Copy disabled (too large)
Download .txt
Showing preview only (16,285K chars total). Download the full file to get everything.
Repository: lllyasviel/stable-diffusion-webui-forge
Branch: main
Commit: dfdcbab685e5
Files: 1490
Total size: 50.8 MB
Directory structure:
gitextract_xvwc7sir/
├── .eslintignore
├── .eslintrc.js
├── .git-blame-ignore-revs
├── .gitignore
├── .pylintrc
├── CHANGELOG.md
├── CITATION.cff
├── CODEOWNERS
├── LICENSE.txt
├── NEWS.md
├── README.md
├── _typos.toml
├── backend/
│ ├── README.md
│ ├── args.py
│ ├── attention.py
│ ├── diffusion_engine/
│ │ ├── base.py
│ │ ├── chroma.py
│ │ ├── flux.py
│ │ ├── sd15.py
│ │ ├── sd20.py
│ │ ├── sd35.py
│ │ └── sdxl.py
│ ├── huggingface/
│ │ ├── Chroma/
│ │ │ ├── model_index.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ ├── config.json
│ │ │ │ └── model.safetensors.index.json
│ │ │ ├── tokenizer/
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer.json
│ │ │ │ └── tokenizer_config.json
│ │ │ └── vae/
│ │ │ └── config.json
│ │ ├── Kwai-Kolors/
│ │ │ └── Kolors/
│ │ │ ├── model_index.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ ├── config.json
│ │ │ │ ├── pytorch_model.bin.index.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.txt
│ │ │ ├── tokenizer/
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.txt
│ │ │ ├── unet/
│ │ │ │ └── config.json
│ │ │ └── vae/
│ │ │ └── config.json
│ │ ├── Tencent-Hunyuan/
│ │ │ └── HunyuanDiT-Diffusers/
│ │ │ ├── model_index.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ └── config.json
│ │ │ ├── text_encoder_2/
│ │ │ │ ├── config.json
│ │ │ │ └── model.safetensors.index.json
│ │ │ ├── tokenizer/
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.txt
│ │ │ ├── tokenizer_2/
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ └── tokenizer_config.json
│ │ │ ├── transformer/
│ │ │ │ └── config.json
│ │ │ └── vae/
│ │ │ └── config.json
│ │ ├── black-forest-labs/
│ │ │ ├── FLUX.1-dev/
│ │ │ │ ├── model_index.json
│ │ │ │ ├── scheduler/
│ │ │ │ │ └── scheduler_config.json
│ │ │ │ ├── text_encoder/
│ │ │ │ │ └── config.json
│ │ │ │ ├── text_encoder_2/
│ │ │ │ │ ├── config.json
│ │ │ │ │ └── model.safetensors.index.json
│ │ │ │ ├── tokenizer/
│ │ │ │ │ ├── merges.txt
│ │ │ │ │ ├── special_tokens_map.json
│ │ │ │ │ ├── tokenizer_config.json
│ │ │ │ │ └── vocab.json
│ │ │ │ ├── tokenizer_2/
│ │ │ │ │ ├── special_tokens_map.json
│ │ │ │ │ ├── tokenizer.json
│ │ │ │ │ └── tokenizer_config.json
│ │ │ │ ├── transformer/
│ │ │ │ │ ├── config.json
│ │ │ │ │ └── diffusion_pytorch_model.safetensors.index.json
│ │ │ │ └── vae/
│ │ │ │ └── config.json
│ │ │ └── FLUX.1-schnell/
│ │ │ ├── model_index.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ └── config.json
│ │ │ ├── text_encoder_2/
│ │ │ │ ├── config.json
│ │ │ │ └── model.safetensors.index.json
│ │ │ ├── tokenizer/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── tokenizer_2/
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer.json
│ │ │ │ └── tokenizer_config.json
│ │ │ ├── transformer/
│ │ │ │ ├── config.json
│ │ │ │ └── diffusion_pytorch_model.safetensors.index.json
│ │ │ └── vae/
│ │ │ └── config.json
│ │ ├── diffusers/
│ │ │ └── stable-diffusion-xl-1.0-inpainting-0.1/
│ │ │ ├── model_index.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ └── config.json
│ │ │ ├── text_encoder_2/
│ │ │ │ └── config.json
│ │ │ ├── tokenizer/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── tokenizer_2/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── unet/
│ │ │ │ └── config.json
│ │ │ └── vae/
│ │ │ └── config.json
│ │ ├── lllyasviel/
│ │ │ └── control_v11p_sd15_canny/
│ │ │ └── config.json
│ │ ├── playgroundai/
│ │ │ └── playground-v2.5-1024px-aesthetic/
│ │ │ ├── model_index.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ └── config.json
│ │ │ ├── text_encoder_2/
│ │ │ │ └── config.json
│ │ │ ├── tokenizer/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── tokenizer_2/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── unet/
│ │ │ │ └── config.json
│ │ │ └── vae/
│ │ │ └── config.json
│ │ ├── runwayml/
│ │ │ ├── stable-diffusion-inpainting/
│ │ │ │ ├── config.json
│ │ │ │ ├── feature_extractor/
│ │ │ │ │ └── preprocessor_config.json
│ │ │ │ ├── model_index.json
│ │ │ │ ├── safety_checker/
│ │ │ │ │ └── config.json
│ │ │ │ ├── scheduler/
│ │ │ │ │ └── scheduler_config.json
│ │ │ │ ├── text_encoder/
│ │ │ │ │ └── config.json
│ │ │ │ ├── tokenizer/
│ │ │ │ │ ├── merges.txt
│ │ │ │ │ ├── special_tokens_map.json
│ │ │ │ │ ├── tokenizer_config.json
│ │ │ │ │ └── vocab.json
│ │ │ │ ├── unet/
│ │ │ │ │ └── config.json
│ │ │ │ └── vae/
│ │ │ │ └── config.json
│ │ │ └── stable-diffusion-v1-5/
│ │ │ ├── feature_extractor/
│ │ │ │ └── preprocessor_config.json
│ │ │ ├── model_index.json
│ │ │ ├── safety_checker/
│ │ │ │ └── config.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ └── config.json
│ │ │ ├── tokenizer/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── unet/
│ │ │ │ └── config.json
│ │ │ └── vae/
│ │ │ └── config.json
│ │ └── stabilityai/
│ │ ├── stable-cascade/
│ │ │ ├── decoder/
│ │ │ │ └── config.json
│ │ │ ├── decoder_lite/
│ │ │ │ └── config.json
│ │ │ ├── model_index.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ └── config.json
│ │ │ ├── tokenizer/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ └── vqgan/
│ │ │ └── config.json
│ │ ├── stable-cascade-prior/
│ │ │ ├── feature_extractor/
│ │ │ │ └── preprocessor_config.json
│ │ │ ├── image_encoder/
│ │ │ │ └── config.json
│ │ │ ├── model_index.json
│ │ │ ├── prior/
│ │ │ │ └── config.json
│ │ │ ├── prior_lite/
│ │ │ │ └── config.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ └── config.json
│ │ │ └── tokenizer/
│ │ │ ├── merges.txt
│ │ │ ├── special_tokens_map.json
│ │ │ ├── tokenizer.json
│ │ │ ├── tokenizer_config.json
│ │ │ └── vocab.json
│ │ ├── stable-diffusion-2-1/
│ │ │ ├── feature_extractor/
│ │ │ │ └── preprocessor_config.json
│ │ │ ├── model_index.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ └── config.json
│ │ │ ├── tokenizer/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── unet/
│ │ │ │ └── config.json
│ │ │ └── vae/
│ │ │ └── config.json
│ │ ├── stable-diffusion-2-inpainting/
│ │ │ ├── feature_extractor/
│ │ │ │ └── preprocessor_config.json
│ │ │ ├── model_index.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ └── config.json
│ │ │ ├── tokenizer/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── unet/
│ │ │ │ └── config.json
│ │ │ └── vae/
│ │ │ └── config.json
│ │ ├── stable-diffusion-3-medium-diffusers/
│ │ │ ├── model_index.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ └── config.json
│ │ │ ├── text_encoder_2/
│ │ │ │ └── config.json
│ │ │ ├── text_encoder_3/
│ │ │ │ ├── config.json
│ │ │ │ ├── model.safetensors.index.fp16.json
│ │ │ │ └── model.safetensors.index.json
│ │ │ ├── tokenizer/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── tokenizer_2/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── tokenizer_3/
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── spiece.model
│ │ │ │ ├── tokenizer.json
│ │ │ │ └── tokenizer_config.json
│ │ │ ├── transformer/
│ │ │ │ └── config.json
│ │ │ └── vae/
│ │ │ └── config.json
│ │ ├── stable-diffusion-x4-upscaler/
│ │ │ ├── low_res_scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── model_index.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ └── config.json
│ │ │ ├── tokenizer/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── unet/
│ │ │ │ ├── .ipynb_checkpoints/
│ │ │ │ │ └── config-checkpoint.json
│ │ │ │ └── config.json
│ │ │ └── vae/
│ │ │ └── config.json
│ │ ├── stable-diffusion-xl-base-1.0/
│ │ │ ├── model_index.json
│ │ │ ├── scheduler/
│ │ │ │ └── scheduler_config.json
│ │ │ ├── text_encoder/
│ │ │ │ └── config.json
│ │ │ ├── text_encoder_2/
│ │ │ │ └── config.json
│ │ │ ├── tokenizer/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── tokenizer_2/
│ │ │ │ ├── merges.txt
│ │ │ │ ├── special_tokens_map.json
│ │ │ │ ├── tokenizer_config.json
│ │ │ │ └── vocab.json
│ │ │ ├── unet/
│ │ │ │ └── config.json
│ │ │ ├── vae/
│ │ │ │ └── config.json
│ │ │ ├── vae_1_0/
│ │ │ │ └── config.json
│ │ │ ├── vae_decoder/
│ │ │ │ └── config.json
│ │ │ └── vae_encoder/
│ │ │ └── config.json
│ │ └── stable-diffusion-xl-refiner-1.0/
│ │ ├── model_index.json
│ │ ├── scheduler/
│ │ │ └── scheduler_config.json
│ │ ├── text_encoder/
│ │ │ └── config.json
│ │ ├── tokenizer/
│ │ │ ├── merges.txt
│ │ │ ├── special_tokens_map.json
│ │ │ ├── tokenizer_config.json
│ │ │ └── vocab.json
│ │ ├── unet/
│ │ │ └── config.json
│ │ ├── vae/
│ │ │ └── config.json
│ │ └── vae_1_0/
│ │ └── config.json
│ ├── loader.py
│ ├── memory_management.py
│ ├── misc/
│ │ ├── checkpoint_pickle.py
│ │ ├── diffusers_state_dict.py
│ │ ├── image_resize.py
│ │ ├── sub_quadratic_attention.py
│ │ └── tomesd.py
│ ├── modules/
│ │ ├── k_diffusion_extra.py
│ │ ├── k_model.py
│ │ └── k_prediction.py
│ ├── nn/
│ │ ├── base.py
│ │ ├── chroma.py
│ │ ├── clip.py
│ │ ├── cnets/
│ │ │ ├── cldm.py
│ │ │ └── t2i_adapter.py
│ │ ├── flux.py
│ │ ├── mmditx.py
│ │ ├── t5.py
│ │ ├── unet.py
│ │ └── vae.py
│ ├── operations.py
│ ├── operations_bnb.py
│ ├── operations_gguf.py
│ ├── patcher/
│ │ ├── base.py
│ │ ├── clip.py
│ │ ├── clipvision.py
│ │ ├── controlnet.py
│ │ ├── lora.py
│ │ ├── unet.py
│ │ └── vae.py
│ ├── sampling/
│ │ ├── condition.py
│ │ └── sampling_function.py
│ ├── shared.py
│ ├── state_dict.py
│ ├── stream.py
│ ├── text_processing/
│ │ ├── classic_engine.py
│ │ ├── emphasis.py
│ │ ├── parsing.py
│ │ ├── t5_engine.py
│ │ └── textual_inversion.py
│ └── utils.py
├── download_supported_configs.py
├── environment-wsl2.yaml
├── extensions-builtin/
│ ├── ScuNET/
│ │ ├── preload.py
│ │ └── scripts/
│ │ └── scunet_model.py
│ ├── SwinIR/
│ │ ├── preload.py
│ │ └── scripts/
│ │ └── swinir_model.py
│ ├── extra-options-section/
│ │ └── scripts/
│ │ └── extra_options_section.py
│ ├── forge_legacy_preprocessors/
│ │ ├── .gitignore
│ │ ├── LICENSE
│ │ ├── annotator/
│ │ │ ├── anime_face_segment/
│ │ │ │ ├── LICENSE
│ │ │ │ └── __init__.py
│ │ │ ├── annotator_path.py
│ │ │ ├── binary/
│ │ │ │ └── __init__.py
│ │ │ ├── canny/
│ │ │ │ └── __init__.py
│ │ │ ├── color/
│ │ │ │ └── __init__.py
│ │ │ ├── densepose/
│ │ │ │ ├── __init__.py
│ │ │ │ └── densepose.py
│ │ │ ├── depth_anything.py
│ │ │ ├── depth_anything_v2.py
│ │ │ ├── hed/
│ │ │ │ └── __init__.py
│ │ │ ├── keypose/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── faster_rcnn_r50_fpn_coco.py
│ │ │ │ └── hrnet_w48_coco_256x192.py
│ │ │ ├── leres/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── leres/
│ │ │ │ │ ├── LICENSE
│ │ │ │ │ ├── Resnet.py
│ │ │ │ │ ├── Resnext_torch.py
│ │ │ │ │ ├── depthmap.py
│ │ │ │ │ ├── multi_depth_model_woauxi.py
│ │ │ │ │ ├── net_tools.py
│ │ │ │ │ └── network_auxi.py
│ │ │ │ └── pix2pix/
│ │ │ │ ├── LICENSE
│ │ │ │ ├── models/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── base_model.py
│ │ │ │ │ ├── base_model_hg.py
│ │ │ │ │ ├── networks.py
│ │ │ │ │ └── pix2pix4depth_model.py
│ │ │ │ ├── options/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── base_options.py
│ │ │ │ │ └── test_options.py
│ │ │ │ └── util/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── get_data.py
│ │ │ │ ├── guidedfilter.py
│ │ │ │ ├── html.py
│ │ │ │ ├── image_pool.py
│ │ │ │ ├── util.py
│ │ │ │ └── visualizer.py
│ │ │ ├── lineart/
│ │ │ │ ├── LICENSE
│ │ │ │ └── __init__.py
│ │ │ ├── lineart_anime/
│ │ │ │ ├── LICENSE
│ │ │ │ └── __init__.py
│ │ │ ├── manga_line/
│ │ │ │ ├── LICENSE
│ │ │ │ └── __init__.py
│ │ │ ├── mediapipe_face/
│ │ │ │ ├── __init__.py
│ │ │ │ └── mediapipe_face_common.py
│ │ │ ├── midas/
│ │ │ │ ├── LICENSE
│ │ │ │ ├── __init__.py
│ │ │ │ ├── api.py
│ │ │ │ ├── midas/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── base_model.py
│ │ │ │ │ ├── blocks.py
│ │ │ │ │ ├── dpt_depth.py
│ │ │ │ │ ├── midas_net.py
│ │ │ │ │ ├── midas_net_custom.py
│ │ │ │ │ ├── transforms.py
│ │ │ │ │ └── vit.py
│ │ │ │ └── utils.py
│ │ │ ├── mlsd/
│ │ │ │ ├── LICENSE
│ │ │ │ ├── __init__.py
│ │ │ │ ├── models/
│ │ │ │ │ ├── mbv2_mlsd_large.py
│ │ │ │ │ └── mbv2_mlsd_tiny.py
│ │ │ │ └── utils.py
│ │ │ ├── mmpkg/
│ │ │ │ ├── mmcv/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── arraymisc/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ └── quantization.py
│ │ │ │ │ ├── cnn/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── alexnet.py
│ │ │ │ │ │ ├── bricks/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── activation.py
│ │ │ │ │ │ │ ├── context_block.py
│ │ │ │ │ │ │ ├── conv.py
│ │ │ │ │ │ │ ├── conv2d_adaptive_padding.py
│ │ │ │ │ │ │ ├── conv_module.py
│ │ │ │ │ │ │ ├── conv_ws.py
│ │ │ │ │ │ │ ├── depthwise_separable_conv_module.py
│ │ │ │ │ │ │ ├── drop.py
│ │ │ │ │ │ │ ├── generalized_attention.py
│ │ │ │ │ │ │ ├── hsigmoid.py
│ │ │ │ │ │ │ ├── hswish.py
│ │ │ │ │ │ │ ├── non_local.py
│ │ │ │ │ │ │ ├── norm.py
│ │ │ │ │ │ │ ├── padding.py
│ │ │ │ │ │ │ ├── plugin.py
│ │ │ │ │ │ │ ├── registry.py
│ │ │ │ │ │ │ ├── scale.py
│ │ │ │ │ │ │ ├── swish.py
│ │ │ │ │ │ │ ├── transformer.py
│ │ │ │ │ │ │ ├── upsample.py
│ │ │ │ │ │ │ └── wrappers.py
│ │ │ │ │ │ ├── builder.py
│ │ │ │ │ │ ├── resnet.py
│ │ │ │ │ │ ├── utils/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── flops_counter.py
│ │ │ │ │ │ │ ├── fuse_conv_bn.py
│ │ │ │ │ │ │ ├── sync_bn.py
│ │ │ │ │ │ │ └── weight_init.py
│ │ │ │ │ │ └── vgg.py
│ │ │ │ │ ├── engine/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ └── test.py
│ │ │ │ │ ├── fileio/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── file_client.py
│ │ │ │ │ │ ├── handlers/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── base.py
│ │ │ │ │ │ │ ├── json_handler.py
│ │ │ │ │ │ │ ├── pickle_handler.py
│ │ │ │ │ │ │ └── yaml_handler.py
│ │ │ │ │ │ ├── io.py
│ │ │ │ │ │ └── parse.py
│ │ │ │ │ ├── image/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── colorspace.py
│ │ │ │ │ │ ├── geometric.py
│ │ │ │ │ │ ├── io.py
│ │ │ │ │ │ ├── misc.py
│ │ │ │ │ │ └── photometric.py
│ │ │ │ │ ├── model_zoo/
│ │ │ │ │ │ ├── deprecated.json
│ │ │ │ │ │ ├── mmcls.json
│ │ │ │ │ │ └── open_mmlab.json
│ │ │ │ │ ├── ops/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── assign_score_withk.py
│ │ │ │ │ │ ├── ball_query.py
│ │ │ │ │ │ ├── bbox.py
│ │ │ │ │ │ ├── border_align.py
│ │ │ │ │ │ ├── box_iou_rotated.py
│ │ │ │ │ │ ├── carafe.py
│ │ │ │ │ │ ├── cc_attention.py
│ │ │ │ │ │ ├── contour_expand.py
│ │ │ │ │ │ ├── corner_pool.py
│ │ │ │ │ │ ├── correlation.py
│ │ │ │ │ │ ├── deform_conv.py
│ │ │ │ │ │ ├── deform_roi_pool.py
│ │ │ │ │ │ ├── deprecated_wrappers.py
│ │ │ │ │ │ ├── focal_loss.py
│ │ │ │ │ │ ├── furthest_point_sample.py
│ │ │ │ │ │ ├── fused_bias_leakyrelu.py
│ │ │ │ │ │ ├── gather_points.py
│ │ │ │ │ │ ├── group_points.py
│ │ │ │ │ │ ├── info.py
│ │ │ │ │ │ ├── iou3d.py
│ │ │ │ │ │ ├── knn.py
│ │ │ │ │ │ ├── masked_conv.py
│ │ │ │ │ │ ├── merge_cells.py
│ │ │ │ │ │ ├── modulated_deform_conv.py
│ │ │ │ │ │ ├── multi_scale_deform_attn.py
│ │ │ │ │ │ ├── nms.py
│ │ │ │ │ │ ├── pixel_group.py
│ │ │ │ │ │ ├── point_sample.py
│ │ │ │ │ │ ├── points_in_boxes.py
│ │ │ │ │ │ ├── points_sampler.py
│ │ │ │ │ │ ├── psa_mask.py
│ │ │ │ │ │ ├── roi_align.py
│ │ │ │ │ │ ├── roi_align_rotated.py
│ │ │ │ │ │ ├── roi_pool.py
│ │ │ │ │ │ ├── roiaware_pool3d.py
│ │ │ │ │ │ ├── roipoint_pool3d.py
│ │ │ │ │ │ ├── saconv.py
│ │ │ │ │ │ ├── scatter_points.py
│ │ │ │ │ │ ├── sync_bn.py
│ │ │ │ │ │ ├── three_interpolate.py
│ │ │ │ │ │ ├── three_nn.py
│ │ │ │ │ │ ├── tin_shift.py
│ │ │ │ │ │ ├── upfirdn2d.py
│ │ │ │ │ │ └── voxelize.py
│ │ │ │ │ ├── parallel/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── _functions.py
│ │ │ │ │ │ ├── collate.py
│ │ │ │ │ │ ├── data_container.py
│ │ │ │ │ │ ├── data_parallel.py
│ │ │ │ │ │ ├── distributed.py
│ │ │ │ │ │ ├── distributed_deprecated.py
│ │ │ │ │ │ ├── registry.py
│ │ │ │ │ │ ├── scatter_gather.py
│ │ │ │ │ │ └── utils.py
│ │ │ │ │ ├── runner/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── base_module.py
│ │ │ │ │ │ ├── base_runner.py
│ │ │ │ │ │ ├── builder.py
│ │ │ │ │ │ ├── checkpoint.py
│ │ │ │ │ │ ├── default_constructor.py
│ │ │ │ │ │ ├── dist_utils.py
│ │ │ │ │ │ ├── epoch_based_runner.py
│ │ │ │ │ │ ├── fp16_utils.py
│ │ │ │ │ │ ├── hooks/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── checkpoint.py
│ │ │ │ │ │ │ ├── closure.py
│ │ │ │ │ │ │ ├── ema.py
│ │ │ │ │ │ │ ├── evaluation.py
│ │ │ │ │ │ │ ├── hook.py
│ │ │ │ │ │ │ ├── iter_timer.py
│ │ │ │ │ │ │ ├── logger/
│ │ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ │ ├── base.py
│ │ │ │ │ │ │ │ ├── dvclive.py
│ │ │ │ │ │ │ │ ├── mlflow.py
│ │ │ │ │ │ │ │ ├── neptune.py
│ │ │ │ │ │ │ │ ├── pavi.py
│ │ │ │ │ │ │ │ ├── tensorboard.py
│ │ │ │ │ │ │ │ ├── text.py
│ │ │ │ │ │ │ │ └── wandb.py
│ │ │ │ │ │ │ ├── lr_updater.py
│ │ │ │ │ │ │ ├── memory.py
│ │ │ │ │ │ │ ├── momentum_updater.py
│ │ │ │ │ │ │ ├── optimizer.py
│ │ │ │ │ │ │ ├── profiler.py
│ │ │ │ │ │ │ ├── sampler_seed.py
│ │ │ │ │ │ │ └── sync_buffer.py
│ │ │ │ │ │ ├── iter_based_runner.py
│ │ │ │ │ │ ├── log_buffer.py
│ │ │ │ │ │ ├── optimizer/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── builder.py
│ │ │ │ │ │ │ └── default_constructor.py
│ │ │ │ │ │ ├── priority.py
│ │ │ │ │ │ └── utils.py
│ │ │ │ │ ├── utils/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── config.py
│ │ │ │ │ │ ├── env.py
│ │ │ │ │ │ ├── ext_loader.py
│ │ │ │ │ │ ├── logging.py
│ │ │ │ │ │ ├── misc.py
│ │ │ │ │ │ ├── parrots_jit.py
│ │ │ │ │ │ ├── parrots_wrapper.py
│ │ │ │ │ │ ├── path.py
│ │ │ │ │ │ ├── progressbar.py
│ │ │ │ │ │ ├── registry.py
│ │ │ │ │ │ ├── testing.py
│ │ │ │ │ │ ├── timer.py
│ │ │ │ │ │ ├── trace.py
│ │ │ │ │ │ └── version_utils.py
│ │ │ │ │ ├── version.py
│ │ │ │ │ ├── video/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── io.py
│ │ │ │ │ │ ├── optflow.py
│ │ │ │ │ │ └── processing.py
│ │ │ │ │ └── visualization/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── color.py
│ │ │ │ │ ├── image.py
│ │ │ │ │ └── optflow.py
│ │ │ │ └── mmseg/
│ │ │ │ ├── apis/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── inference.py
│ │ │ │ │ ├── test.py
│ │ │ │ │ └── train.py
│ │ │ │ ├── core/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── evaluation/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── class_names.py
│ │ │ │ │ │ ├── eval_hooks.py
│ │ │ │ │ │ └── metrics.py
│ │ │ │ │ ├── seg/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── builder.py
│ │ │ │ │ │ └── sampler/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── base_pixel_sampler.py
│ │ │ │ │ │ └── ohem_pixel_sampler.py
│ │ │ │ │ └── utils/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ └── misc.py
│ │ │ │ ├── datasets/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── ade.py
│ │ │ │ │ ├── builder.py
│ │ │ │ │ ├── chase_db1.py
│ │ │ │ │ ├── cityscapes.py
│ │ │ │ │ ├── custom.py
│ │ │ │ │ ├── dataset_wrappers.py
│ │ │ │ │ ├── drive.py
│ │ │ │ │ ├── hrf.py
│ │ │ │ │ ├── pascal_context.py
│ │ │ │ │ ├── pipelines/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── compose.py
│ │ │ │ │ │ ├── formating.py
│ │ │ │ │ │ ├── loading.py
│ │ │ │ │ │ ├── test_time_aug.py
│ │ │ │ │ │ └── transforms.py
│ │ │ │ │ ├── stare.py
│ │ │ │ │ └── voc.py
│ │ │ │ ├── models/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── backbones/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── cgnet.py
│ │ │ │ │ │ ├── fast_scnn.py
│ │ │ │ │ │ ├── hrnet.py
│ │ │ │ │ │ ├── mobilenet_v2.py
│ │ │ │ │ │ ├── mobilenet_v3.py
│ │ │ │ │ │ ├── resnest.py
│ │ │ │ │ │ ├── resnet.py
│ │ │ │ │ │ ├── resnext.py
│ │ │ │ │ │ ├── unet.py
│ │ │ │ │ │ └── vit.py
│ │ │ │ │ ├── builder.py
│ │ │ │ │ ├── decode_heads/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── ann_head.py
│ │ │ │ │ │ ├── apc_head.py
│ │ │ │ │ │ ├── aspp_head.py
│ │ │ │ │ │ ├── cascade_decode_head.py
│ │ │ │ │ │ ├── cc_head.py
│ │ │ │ │ │ ├── da_head.py
│ │ │ │ │ │ ├── decode_head.py
│ │ │ │ │ │ ├── dm_head.py
│ │ │ │ │ │ ├── dnl_head.py
│ │ │ │ │ │ ├── ema_head.py
│ │ │ │ │ │ ├── enc_head.py
│ │ │ │ │ │ ├── fcn_head.py
│ │ │ │ │ │ ├── fpn_head.py
│ │ │ │ │ │ ├── gc_head.py
│ │ │ │ │ │ ├── lraspp_head.py
│ │ │ │ │ │ ├── nl_head.py
│ │ │ │ │ │ ├── ocr_head.py
│ │ │ │ │ │ ├── point_head.py
│ │ │ │ │ │ ├── psa_head.py
│ │ │ │ │ │ ├── psp_head.py
│ │ │ │ │ │ ├── sep_aspp_head.py
│ │ │ │ │ │ ├── sep_fcn_head.py
│ │ │ │ │ │ └── uper_head.py
│ │ │ │ │ ├── losses/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── accuracy.py
│ │ │ │ │ │ ├── cross_entropy_loss.py
│ │ │ │ │ │ ├── dice_loss.py
│ │ │ │ │ │ ├── lovasz_loss.py
│ │ │ │ │ │ └── utils.py
│ │ │ │ │ ├── necks/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── fpn.py
│ │ │ │ │ │ └── multilevel_neck.py
│ │ │ │ │ ├── segmentors/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── base.py
│ │ │ │ │ │ ├── cascade_encoder_decoder.py
│ │ │ │ │ │ └── encoder_decoder.py
│ │ │ │ │ └── utils/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── drop.py
│ │ │ │ │ ├── inverted_residual.py
│ │ │ │ │ ├── make_divisible.py
│ │ │ │ │ ├── res_layer.py
│ │ │ │ │ ├── se_layer.py
│ │ │ │ │ ├── self_attention_block.py
│ │ │ │ │ ├── up_conv_block.py
│ │ │ │ │ └── weight_init.py
│ │ │ │ ├── ops/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── encoding.py
│ │ │ │ │ └── wrappers.py
│ │ │ │ └── utils/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── collect_env.py
│ │ │ │ └── logger.py
│ │ │ ├── oneformer/
│ │ │ │ ├── LICENSE
│ │ │ │ ├── __init__.py
│ │ │ │ ├── api.py
│ │ │ │ ├── configs/
│ │ │ │ │ ├── ade20k/
│ │ │ │ │ │ ├── Base-ADE20K-UnifiedSegmentation.yaml
│ │ │ │ │ │ ├── oneformer_R50_bs16_160k.yaml
│ │ │ │ │ │ └── oneformer_swin_large_IN21k_384_bs16_160k.yaml
│ │ │ │ │ └── coco/
│ │ │ │ │ ├── Base-COCO-UnifiedSegmentation.yaml
│ │ │ │ │ ├── oneformer_R50_bs16_50ep.yaml
│ │ │ │ │ └── oneformer_swin_large_IN21k_384_bs16_100ep.yaml
│ │ │ │ ├── detectron2/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── checkpoint/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── c2_model_loading.py
│ │ │ │ │ │ ├── catalog.py
│ │ │ │ │ │ └── detection_checkpoint.py
│ │ │ │ │ ├── config/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── compat.py
│ │ │ │ │ │ ├── config.py
│ │ │ │ │ │ ├── defaults.py
│ │ │ │ │ │ ├── instantiate.py
│ │ │ │ │ │ └── lazy.py
│ │ │ │ │ ├── data/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── benchmark.py
│ │ │ │ │ │ ├── build.py
│ │ │ │ │ │ ├── catalog.py
│ │ │ │ │ │ ├── common.py
│ │ │ │ │ │ ├── dataset_mapper.py
│ │ │ │ │ │ ├── datasets/
│ │ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── builtin.py
│ │ │ │ │ │ │ ├── builtin_meta.py
│ │ │ │ │ │ │ ├── cityscapes.py
│ │ │ │ │ │ │ ├── cityscapes_panoptic.py
│ │ │ │ │ │ │ ├── coco.py
│ │ │ │ │ │ │ ├── coco_panoptic.py
│ │ │ │ │ │ │ ├── lvis.py
│ │ │ │ │ │ │ ├── lvis_v0_5_categories.py
│ │ │ │ │ │ │ ├── lvis_v1_categories.py
│ │ │ │ │ │ │ ├── lvis_v1_category_image_count.py
│ │ │ │ │ │ │ ├── pascal_voc.py
│ │ │ │ │ │ │ └── register_coco.py
│ │ │ │ │ │ ├── detection_utils.py
│ │ │ │ │ │ ├── samplers/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── distributed_sampler.py
│ │ │ │ │ │ │ └── grouped_batch_sampler.py
│ │ │ │ │ │ └── transforms/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── augmentation.py
│ │ │ │ │ │ ├── augmentation_impl.py
│ │ │ │ │ │ └── transform.py
│ │ │ │ │ ├── engine/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── defaults.py
│ │ │ │ │ │ ├── hooks.py
│ │ │ │ │ │ ├── launch.py
│ │ │ │ │ │ └── train_loop.py
│ │ │ │ │ ├── evaluation/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── cityscapes_evaluation.py
│ │ │ │ │ │ ├── coco_evaluation.py
│ │ │ │ │ │ ├── evaluator.py
│ │ │ │ │ │ ├── fast_eval_api.py
│ │ │ │ │ │ ├── lvis_evaluation.py
│ │ │ │ │ │ ├── panoptic_evaluation.py
│ │ │ │ │ │ ├── pascal_voc_evaluation.py
│ │ │ │ │ │ ├── rotated_coco_evaluation.py
│ │ │ │ │ │ ├── sem_seg_evaluation.py
│ │ │ │ │ │ └── testing.py
│ │ │ │ │ ├── export/
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── api.py
│ │ │ │ │ │ ├── c10.py
│ │ │ │ │ │ ├── caffe2_export.py
│ │ │ │ │ │ ├── caffe2_inference.py
│ │ │ │ │ │ ├── caffe2_modeling.py
│ │ │ │ │ │ ├── caffe2_patch.py
│ │ │ │ │ │ ├── flatten.py
│ │ │ │ │ │ ├── shared.py
│ │ │ │ │ │ ├── torchscript.py
│ │ │ │ │ │ └── torchscript_patch.py
│ │ │ │ │ ├── layers/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── aspp.py
│ │ │ │ │ │ ├── batch_norm.py
│ │ │ │ │ │ ├── blocks.py
│ │ │ │ │ │ ├── csrc/
│ │ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ │ ├── ROIAlignRotated/
│ │ │ │ │ │ │ │ ├── ROIAlignRotated.h
│ │ │ │ │ │ │ │ ├── ROIAlignRotated_cpu.cpp
│ │ │ │ │ │ │ │ └── ROIAlignRotated_cuda.cu
│ │ │ │ │ │ │ ├── box_iou_rotated/
│ │ │ │ │ │ │ │ ├── box_iou_rotated.h
│ │ │ │ │ │ │ │ ├── box_iou_rotated_cpu.cpp
│ │ │ │ │ │ │ │ ├── box_iou_rotated_cuda.cu
│ │ │ │ │ │ │ │ └── box_iou_rotated_utils.h
│ │ │ │ │ │ │ ├── cocoeval/
│ │ │ │ │ │ │ │ ├── cocoeval.cpp
│ │ │ │ │ │ │ │ └── cocoeval.h
│ │ │ │ │ │ │ ├── cuda_version.cu
│ │ │ │ │ │ │ ├── deformable/
│ │ │ │ │ │ │ │ ├── deform_conv.h
│ │ │ │ │ │ │ │ ├── deform_conv_cuda.cu
│ │ │ │ │ │ │ │ └── deform_conv_cuda_kernel.cu
│ │ │ │ │ │ │ ├── nms_rotated/
│ │ │ │ │ │ │ │ ├── nms_rotated.h
│ │ │ │ │ │ │ │ ├── nms_rotated_cpu.cpp
│ │ │ │ │ │ │ │ └── nms_rotated_cuda.cu
│ │ │ │ │ │ │ └── vision.cpp
│ │ │ │ │ │ ├── deform_conv.py
│ │ │ │ │ │ ├── losses.py
│ │ │ │ │ │ ├── mask_ops.py
│ │ │ │ │ │ ├── nms.py
│ │ │ │ │ │ ├── roi_align.py
│ │ │ │ │ │ ├── roi_align_rotated.py
│ │ │ │ │ │ ├── rotated_boxes.py
│ │ │ │ │ │ ├── shape_spec.py
│ │ │ │ │ │ └── wrappers.py
│ │ │ │ │ ├── model_zoo/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ └── model_zoo.py
│ │ │ │ │ ├── modeling/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── anchor_generator.py
│ │ │ │ │ │ ├── backbone/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── backbone.py
│ │ │ │ │ │ │ ├── build.py
│ │ │ │ │ │ │ ├── fpn.py
│ │ │ │ │ │ │ ├── mvit.py
│ │ │ │ │ │ │ ├── regnet.py
│ │ │ │ │ │ │ ├── resnet.py
│ │ │ │ │ │ │ ├── swin.py
│ │ │ │ │ │ │ ├── utils.py
│ │ │ │ │ │ │ └── vit.py
│ │ │ │ │ │ ├── box_regression.py
│ │ │ │ │ │ ├── matcher.py
│ │ │ │ │ │ ├── meta_arch/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── build.py
│ │ │ │ │ │ │ ├── dense_detector.py
│ │ │ │ │ │ │ ├── fcos.py
│ │ │ │ │ │ │ ├── panoptic_fpn.py
│ │ │ │ │ │ │ ├── rcnn.py
│ │ │ │ │ │ │ ├── retinanet.py
│ │ │ │ │ │ │ └── semantic_seg.py
│ │ │ │ │ │ ├── mmdet_wrapper.py
│ │ │ │ │ │ ├── poolers.py
│ │ │ │ │ │ ├── postprocessing.py
│ │ │ │ │ │ ├── proposal_generator/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── build.py
│ │ │ │ │ │ │ ├── proposal_utils.py
│ │ │ │ │ │ │ ├── rpn.py
│ │ │ │ │ │ │ └── rrpn.py
│ │ │ │ │ │ ├── roi_heads/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── box_head.py
│ │ │ │ │ │ │ ├── cascade_rcnn.py
│ │ │ │ │ │ │ ├── fast_rcnn.py
│ │ │ │ │ │ │ ├── keypoint_head.py
│ │ │ │ │ │ │ ├── mask_head.py
│ │ │ │ │ │ │ ├── roi_heads.py
│ │ │ │ │ │ │ └── rotated_fast_rcnn.py
│ │ │ │ │ │ ├── sampling.py
│ │ │ │ │ │ └── test_time_augmentation.py
│ │ │ │ │ ├── projects/
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ └── deeplab/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── build_solver.py
│ │ │ │ │ │ ├── config.py
│ │ │ │ │ │ ├── loss.py
│ │ │ │ │ │ ├── lr_scheduler.py
│ │ │ │ │ │ ├── resnet.py
│ │ │ │ │ │ └── semantic_seg.py
│ │ │ │ │ ├── solver/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── build.py
│ │ │ │ │ │ └── lr_scheduler.py
│ │ │ │ │ ├── structures/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── boxes.py
│ │ │ │ │ │ ├── image_list.py
│ │ │ │ │ │ ├── instances.py
│ │ │ │ │ │ ├── keypoints.py
│ │ │ │ │ │ ├── masks.py
│ │ │ │ │ │ └── rotated_boxes.py
│ │ │ │ │ ├── tracking/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── base_tracker.py
│ │ │ │ │ │ ├── bbox_iou_tracker.py
│ │ │ │ │ │ ├── hungarian_tracker.py
│ │ │ │ │ │ ├── iou_weighted_hungarian_bbox_iou_tracker.py
│ │ │ │ │ │ ├── utils.py
│ │ │ │ │ │ └── vanilla_hungarian_bbox_iou_tracker.py
│ │ │ │ │ └── utils/
│ │ │ │ │ ├── README.md
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── analysis.py
│ │ │ │ │ ├── collect_env.py
│ │ │ │ │ ├── colormap.py
│ │ │ │ │ ├── comm.py
│ │ │ │ │ ├── develop.py
│ │ │ │ │ ├── env.py
│ │ │ │ │ ├── events.py
│ │ │ │ │ ├── file_io.py
│ │ │ │ │ ├── logger.py
│ │ │ │ │ ├── memory.py
│ │ │ │ │ ├── registry.py
│ │ │ │ │ ├── serialize.py
│ │ │ │ │ ├── testing.py
│ │ │ │ │ ├── tracing.py
│ │ │ │ │ ├── video_visualizer.py
│ │ │ │ │ └── visualizer.py
│ │ │ │ ├── oneformer/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── config.py
│ │ │ │ │ ├── data/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── build.py
│ │ │ │ │ │ ├── dataset_mappers/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── coco_unified_new_baseline_dataset_mapper.py
│ │ │ │ │ │ │ ├── dataset_mapper.py
│ │ │ │ │ │ │ └── oneformer_unified_dataset_mapper.py
│ │ │ │ │ │ ├── datasets/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── register_ade20k_instance.py
│ │ │ │ │ │ │ ├── register_ade20k_panoptic.py
│ │ │ │ │ │ │ ├── register_cityscapes_panoptic.py
│ │ │ │ │ │ │ ├── register_coco_panoptic2instance.py
│ │ │ │ │ │ │ └── register_coco_panoptic_annos_semseg.py
│ │ │ │ │ │ └── tokenizer.py
│ │ │ │ │ ├── demo/
│ │ │ │ │ │ ├── colormap.py
│ │ │ │ │ │ ├── defaults.py
│ │ │ │ │ │ ├── predictor.py
│ │ │ │ │ │ └── visualizer.py
│ │ │ │ │ ├── evaluation/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── cityscapes_evaluation.py
│ │ │ │ │ │ ├── coco_evaluator.py
│ │ │ │ │ │ ├── detection_coco_evaluator.py
│ │ │ │ │ │ ├── evaluator.py
│ │ │ │ │ │ └── instance_evaluation.py
│ │ │ │ │ ├── modeling/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── backbone/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── dinat.py
│ │ │ │ │ │ │ └── swin.py
│ │ │ │ │ │ ├── matcher.py
│ │ │ │ │ │ ├── meta_arch/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ └── oneformer_head.py
│ │ │ │ │ │ ├── pixel_decoder/
│ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ ├── fpn.py
│ │ │ │ │ │ │ ├── msdeformattn.py
│ │ │ │ │ │ │ └── ops/
│ │ │ │ │ │ │ ├── functions/
│ │ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ │ └── ms_deform_attn_func.py
│ │ │ │ │ │ │ ├── make.sh
│ │ │ │ │ │ │ ├── modules/
│ │ │ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ │ │ └── ms_deform_attn.py
│ │ │ │ │ │ │ ├── setup.py
│ │ │ │ │ │ │ ├── src/
│ │ │ │ │ │ │ │ ├── cpu/
│ │ │ │ │ │ │ │ │ ├── ms_deform_attn_cpu.cpp
│ │ │ │ │ │ │ │ │ └── ms_deform_attn_cpu.h
│ │ │ │ │ │ │ │ ├── cuda/
│ │ │ │ │ │ │ │ │ ├── ms_deform_attn_cuda.cu
│ │ │ │ │ │ │ │ │ ├── ms_deform_attn_cuda.h
│ │ │ │ │ │ │ │ │ └── ms_deform_im2col_cuda.cuh
│ │ │ │ │ │ │ │ ├── ms_deform_attn.h
│ │ │ │ │ │ │ │ └── vision.cpp
│ │ │ │ │ │ │ └── test.py
│ │ │ │ │ │ └── transformer_decoder/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── oneformer_transformer_decoder.py
│ │ │ │ │ │ ├── position_encoding.py
│ │ │ │ │ │ ├── text_transformer.py
│ │ │ │ │ │ └── transformer.py
│ │ │ │ │ ├── oneformer_model.py
│ │ │ │ │ └── utils/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── box_ops.py
│ │ │ │ │ ├── events.py
│ │ │ │ │ ├── misc.py
│ │ │ │ │ └── pos_embed.py
│ │ │ │ └── pycocotools/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── coco.py
│ │ │ │ ├── cocoeval.py
│ │ │ │ └── mask.py
│ │ │ ├── openpose/
│ │ │ │ ├── LICENSE
│ │ │ │ ├── __init__.py
│ │ │ │ ├── animalpose.py
│ │ │ │ ├── body.py
│ │ │ │ ├── cv_ox_det.py
│ │ │ │ ├── cv_ox_pose.py
│ │ │ │ ├── face.py
│ │ │ │ ├── hand.py
│ │ │ │ ├── model.py
│ │ │ │ ├── types.py
│ │ │ │ ├── util.py
│ │ │ │ └── wholebody.py
│ │ │ ├── pidinet/
│ │ │ │ ├── LICENSE
│ │ │ │ ├── __init__.py
│ │ │ │ └── model.py
│ │ │ ├── shuffle/
│ │ │ │ └── __init__.py
│ │ │ ├── teed/
│ │ │ │ ├── Fmish.py
│ │ │ │ ├── Fsmish.py
│ │ │ │ ├── LICENSE.txt
│ │ │ │ ├── Xmish.py
│ │ │ │ ├── Xsmish.py
│ │ │ │ ├── __init__.py
│ │ │ │ └── ted.py
│ │ │ ├── uniformer/
│ │ │ │ ├── LICENSE
│ │ │ │ ├── __init__.py
│ │ │ │ ├── configs/
│ │ │ │ │ └── _base_/
│ │ │ │ │ ├── datasets/
│ │ │ │ │ │ ├── ade20k.py
│ │ │ │ │ │ ├── chase_db1.py
│ │ │ │ │ │ ├── cityscapes.py
│ │ │ │ │ │ ├── cityscapes_769x769.py
│ │ │ │ │ │ ├── drive.py
│ │ │ │ │ │ ├── hrf.py
│ │ │ │ │ │ ├── pascal_context.py
│ │ │ │ │ │ ├── pascal_context_59.py
│ │ │ │ │ │ ├── pascal_voc12.py
│ │ │ │ │ │ ├── pascal_voc12_aug.py
│ │ │ │ │ │ └── stare.py
│ │ │ │ │ ├── default_runtime.py
│ │ │ │ │ ├── models/
│ │ │ │ │ │ ├── ann_r50-d8.py
│ │ │ │ │ │ ├── apcnet_r50-d8.py
│ │ │ │ │ │ ├── ccnet_r50-d8.py
│ │ │ │ │ │ ├── cgnet.py
│ │ │ │ │ │ ├── danet_r50-d8.py
│ │ │ │ │ │ ├── deeplabv3_r50-d8.py
│ │ │ │ │ │ ├── deeplabv3_unet_s5-d16.py
│ │ │ │ │ │ ├── deeplabv3plus_r50-d8.py
│ │ │ │ │ │ ├── dmnet_r50-d8.py
│ │ │ │ │ │ ├── dnl_r50-d8.py
│ │ │ │ │ │ ├── emanet_r50-d8.py
│ │ │ │ │ │ ├── encnet_r50-d8.py
│ │ │ │ │ │ ├── fast_scnn.py
│ │ │ │ │ │ ├── fcn_hr18.py
│ │ │ │ │ │ ├── fcn_r50-d8.py
│ │ │ │ │ │ ├── fcn_unet_s5-d16.py
│ │ │ │ │ │ ├── fpn_r50.py
│ │ │ │ │ │ ├── fpn_uniformer.py
│ │ │ │ │ │ ├── gcnet_r50-d8.py
│ │ │ │ │ │ ├── lraspp_m-v3-d8.py
│ │ │ │ │ │ ├── nonlocal_r50-d8.py
│ │ │ │ │ │ ├── ocrnet_hr18.py
│ │ │ │ │ │ ├── ocrnet_r50-d8.py
│ │ │ │ │ │ ├── pointrend_r50.py
│ │ │ │ │ │ ├── psanet_r50-d8.py
│ │ │ │ │ │ ├── pspnet_r50-d8.py
│ │ │ │ │ │ ├── pspnet_unet_s5-d16.py
│ │ │ │ │ │ ├── upernet_r50.py
│ │ │ │ │ │ └── upernet_uniformer.py
│ │ │ │ │ └── schedules/
│ │ │ │ │ ├── schedule_160k.py
│ │ │ │ │ ├── schedule_20k.py
│ │ │ │ │ ├── schedule_40k.py
│ │ │ │ │ └── schedule_80k.py
│ │ │ │ ├── inference.py
│ │ │ │ ├── mmcv_custom/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ └── checkpoint.py
│ │ │ │ ├── uniformer.py
│ │ │ │ └── upernet_global_small.py
│ │ │ ├── util.py
│ │ │ └── zoe/
│ │ │ ├── LICENSE
│ │ │ ├── __init__.py
│ │ │ └── zoedepth/
│ │ │ ├── models/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── base_models/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── midas.py
│ │ │ │ │ └── midas_repo/
│ │ │ │ │ ├── .gitignore
│ │ │ │ │ ├── Dockerfile
│ │ │ │ │ ├── LICENSE
│ │ │ │ │ ├── README.md
│ │ │ │ │ ├── environment.yaml
│ │ │ │ │ ├── hubconf.py
│ │ │ │ │ ├── input/
│ │ │ │ │ │ └── .placeholder
│ │ │ │ │ ├── midas/
│ │ │ │ │ │ ├── backbones/
│ │ │ │ │ │ │ ├── beit.py
│ │ │ │ │ │ │ ├── levit.py
│ │ │ │ │ │ │ ├── next_vit.py
│ │ │ │ │ │ │ ├── swin.py
│ │ │ │ │ │ │ ├── swin2.py
│ │ │ │ │ │ │ ├── swin_common.py
│ │ │ │ │ │ │ ├── utils.py
│ │ │ │ │ │ │ └── vit.py
│ │ │ │ │ │ ├── base_model.py
│ │ │ │ │ │ ├── blocks.py
│ │ │ │ │ │ ├── dpt_depth.py
│ │ │ │ │ │ ├── midas_net.py
│ │ │ │ │ │ ├── midas_net_custom.py
│ │ │ │ │ │ ├── model_loader.py
│ │ │ │ │ │ └── transforms.py
│ │ │ │ │ ├── output/
│ │ │ │ │ │ └── .placeholder
│ │ │ │ │ ├── ros/
│ │ │ │ │ │ ├── LICENSE
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ ├── additions/
│ │ │ │ │ │ │ ├── do_catkin_make.sh
│ │ │ │ │ │ │ ├── downloads.sh
│ │ │ │ │ │ │ ├── install_ros_melodic_ubuntu_17_18.sh
│ │ │ │ │ │ │ ├── install_ros_noetic_ubuntu_20.sh
│ │ │ │ │ │ │ └── make_package_cpp.sh
│ │ │ │ │ │ ├── launch_midas_cpp.sh
│ │ │ │ │ │ ├── midas_cpp/
│ │ │ │ │ │ │ ├── CMakeLists.txt
│ │ │ │ │ │ │ ├── launch/
│ │ │ │ │ │ │ │ ├── midas_cpp.launch
│ │ │ │ │ │ │ │ └── midas_talker_listener.launch
│ │ │ │ │ │ │ ├── package.xml
│ │ │ │ │ │ │ ├── scripts/
│ │ │ │ │ │ │ │ ├── listener.py
│ │ │ │ │ │ │ │ ├── listener_original.py
│ │ │ │ │ │ │ │ └── talker.py
│ │ │ │ │ │ │ └── src/
│ │ │ │ │ │ │ └── main.cpp
│ │ │ │ │ │ └── run_talker_listener_test.sh
│ │ │ │ │ ├── run.py
│ │ │ │ │ ├── tf/
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ ├── input/
│ │ │ │ │ │ │ └── .placeholder
│ │ │ │ │ │ ├── make_onnx_model.py
│ │ │ │ │ │ ├── output/
│ │ │ │ │ │ │ └── .placeholder
│ │ │ │ │ │ ├── run_onnx.py
│ │ │ │ │ │ ├── run_pb.py
│ │ │ │ │ │ ├── transforms.py
│ │ │ │ │ │ └── utils.py
│ │ │ │ │ ├── utils.py
│ │ │ │ │ └── weights/
│ │ │ │ │ └── .placeholder
│ │ │ │ ├── builder.py
│ │ │ │ ├── depth_model.py
│ │ │ │ ├── layers/
│ │ │ │ │ ├── attractor.py
│ │ │ │ │ ├── dist_layers.py
│ │ │ │ │ ├── localbins_layers.py
│ │ │ │ │ └── patch_transformer.py
│ │ │ │ ├── model_io.py
│ │ │ │ ├── zoedepth/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── config_zoedepth.json
│ │ │ │ │ ├── config_zoedepth_kitti.json
│ │ │ │ │ └── zoedepth_v1.py
│ │ │ │ └── zoedepth_nk/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── config_zoedepth_nk.json
│ │ │ │ └── zoedepth_nk_v1.py
│ │ │ └── utils/
│ │ │ ├── __init__.py
│ │ │ ├── arg_utils.py
│ │ │ ├── config.py
│ │ │ ├── easydict/
│ │ │ │ └── __init__.py
│ │ │ ├── geometry.py
│ │ │ └── misc.py
│ │ ├── install.py
│ │ ├── legacy_preprocessors/
│ │ │ ├── preprocessor.py
│ │ │ └── preprocessor_compiled.py
│ │ ├── requirements.txt
│ │ └── scripts/
│ │ └── legacy_preprocessors.py
│ ├── forge_preprocessor_inpaint/
│ │ ├── annotator/
│ │ │ └── lama/
│ │ │ └── saicinpainting/
│ │ │ ├── __init__.py
│ │ │ ├── training/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── data/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ └── masks.py
│ │ │ │ ├── losses/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── adversarial.py
│ │ │ │ │ ├── constants.py
│ │ │ │ │ ├── distance_weighting.py
│ │ │ │ │ ├── feature_matching.py
│ │ │ │ │ ├── perceptual.py
│ │ │ │ │ ├── segmentation.py
│ │ │ │ │ └── style_loss.py
│ │ │ │ ├── modules/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── base.py
│ │ │ │ │ ├── depthwise_sep_conv.py
│ │ │ │ │ ├── fake_fakes.py
│ │ │ │ │ ├── ffc.py
│ │ │ │ │ ├── multidilated_conv.py
│ │ │ │ │ ├── multiscale.py
│ │ │ │ │ ├── pix2pixhd.py
│ │ │ │ │ ├── spatial_transform.py
│ │ │ │ │ └── squeeze_excitation.py
│ │ │ │ ├── trainers/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── base.py
│ │ │ │ │ └── default.py
│ │ │ │ └── visualizers/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── base.py
│ │ │ │ ├── colors.py
│ │ │ │ ├── directory.py
│ │ │ │ └── noop.py
│ │ │ └── utils.py
│ │ └── scripts/
│ │ ├── lama_config.yaml
│ │ └── preprocessor_inpaint.py
│ ├── forge_preprocessor_marigold/
│ │ ├── marigold/
│ │ │ ├── model/
│ │ │ │ ├── __init__.py
│ │ │ │ ├── marigold_pipeline.py
│ │ │ │ ├── rgb_encoder.py
│ │ │ │ └── stacked_depth_AE.py
│ │ │ └── util/
│ │ │ ├── batchsize.py
│ │ │ ├── ensemble.py
│ │ │ ├── image_util.py
│ │ │ └── seed_all.py
│ │ └── scripts/
│ │ └── preprocessor_marigold.py
│ ├── forge_preprocessor_normalbae/
│ │ ├── annotator/
│ │ │ └── normalbae/
│ │ │ ├── LICENSE
│ │ │ ├── __init__.py
│ │ │ └── models/
│ │ │ ├── NNET.py
│ │ │ ├── baseline.py
│ │ │ └── submodules/
│ │ │ ├── decoder.py
│ │ │ ├── efficientnet_repo/
│ │ │ │ ├── .gitignore
│ │ │ │ ├── BENCHMARK.md
│ │ │ │ ├── LICENSE
│ │ │ │ ├── README.md
│ │ │ │ ├── caffe2_benchmark.py
│ │ │ │ ├── caffe2_validate.py
│ │ │ │ ├── geffnet/
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── activations/
│ │ │ │ │ │ ├── __init__.py
│ │ │ │ │ │ ├── activations.py
│ │ │ │ │ │ ├── activations_jit.py
│ │ │ │ │ │ └── activations_me.py
│ │ │ │ │ ├── config.py
│ │ │ │ │ ├── conv2d_layers.py
│ │ │ │ │ ├── efficientnet_builder.py
│ │ │ │ │ ├── gen_efficientnet.py
│ │ │ │ │ ├── helpers.py
│ │ │ │ │ ├── mobilenetv3.py
│ │ │ │ │ ├── model_factory.py
│ │ │ │ │ └── version.py
│ │ │ │ ├── hubconf.py
│ │ │ │ ├── onnx_export.py
│ │ │ │ ├── onnx_optimize.py
│ │ │ │ ├── onnx_to_caffe.py
│ │ │ │ ├── onnx_validate.py
│ │ │ │ ├── requirements.txt
│ │ │ │ ├── setup.py
│ │ │ │ ├── utils.py
│ │ │ │ └── validate.py
│ │ │ ├── encoder.py
│ │ │ └── submodules.py
│ │ └── scripts/
│ │ └── preprocessor_normalbae.py
│ ├── forge_preprocessor_recolor/
│ │ └── scripts/
│ │ └── preprocessor_recolor.py
│ ├── forge_preprocessor_reference/
│ │ └── scripts/
│ │ └── forge_reference.py
│ ├── forge_preprocessor_revision/
│ │ └── scripts/
│ │ └── preprocessor_revision.py
│ ├── forge_preprocessor_tile/
│ │ └── scripts/
│ │ └── preprocessor_tile.py
│ ├── forge_space_animagine_xl_31/
│ │ ├── forge_app.py
│ │ └── space_meta.json
│ ├── forge_space_birefnet/
│ │ ├── forge_app.py
│ │ └── space_meta.json
│ ├── forge_space_example/
│ │ ├── forge_app.py
│ │ └── space_meta.json
│ ├── forge_space_florence_2/
│ │ ├── forge_app.py
│ │ └── space_meta.json
│ ├── forge_space_geowizard/
│ │ ├── forge_app.py
│ │ ├── geo_models/
│ │ │ ├── attention.py
│ │ │ ├── geowizard_pipeline.py
│ │ │ ├── transformer_2d.py
│ │ │ ├── unet_2d_blocks.py
│ │ │ └── unet_2d_condition.py
│ │ ├── geo_utils/
│ │ │ ├── batch_size.py
│ │ │ ├── colormap.py
│ │ │ ├── common.py
│ │ │ ├── dataset_configuration.py
│ │ │ ├── de_normalized.py
│ │ │ ├── depth2normal.py
│ │ │ ├── depth_ensemble.py
│ │ │ ├── image_util.py
│ │ │ ├── normal_ensemble.py
│ │ │ ├── seed_all.py
│ │ │ └── surface_normal.py
│ │ └── space_meta.json
│ ├── forge_space_iclight/
│ │ ├── forge_app.py
│ │ └── space_meta.json
│ ├── forge_space_idm_vton/
│ │ ├── forge_app.py
│ │ ├── requirements.txt
│ │ ├── space_meta.json
│ │ └── src/
│ │ ├── attentionhacked_garmnet.py
│ │ ├── attentionhacked_tryon.py
│ │ ├── transformerhacked_garmnet.py
│ │ ├── transformerhacked_tryon.py
│ │ ├── tryon_pipeline.py
│ │ ├── unet_block_hacked_garmnet.py
│ │ ├── unet_block_hacked_tryon.py
│ │ ├── unet_hacked_garmnet.py
│ │ └── unet_hacked_tryon.py
│ ├── forge_space_illusion_diffusion/
│ │ ├── forge_app.py
│ │ └── space_meta.json
│ ├── forge_space_photo_maker_v2/
│ │ ├── forge_app.py
│ │ └── space_meta.json
│ ├── forge_space_sapiens_normal/
│ │ ├── forge_app.py
│ │ └── space_meta.json
│ ├── mobile/
│ │ └── javascript/
│ │ └── mobile.js
│ ├── prompt-bracket-checker/
│ │ └── javascript/
│ │ └── prompt-bracket-checker.js
│ ├── sd_forge_controlllite/
│ │ ├── lib_controllllite/
│ │ │ └── lib_controllllite.py
│ │ └── scripts/
│ │ └── forge_controllllite.py
│ ├── sd_forge_controlnet/
│ │ ├── .gitignore
│ │ ├── LICENSE
│ │ ├── install.py
│ │ ├── javascript/
│ │ │ ├── active_units.js
│ │ │ ├── canvas.js
│ │ │ ├── modal.js
│ │ │ ├── openpose_editor.js
│ │ │ └── photopea.js
│ │ ├── lib_controlnet/
│ │ │ ├── api.py
│ │ │ ├── controlnet_ui/
│ │ │ │ ├── controlnet_ui_group.py
│ │ │ │ ├── modal.py
│ │ │ │ ├── openpose_editor.py
│ │ │ │ └── photopea.py
│ │ │ ├── enums.py
│ │ │ ├── external_code.py
│ │ │ ├── global_state.py
│ │ │ ├── infotext.py
│ │ │ ├── logging.py
│ │ │ ├── lvminthin.py
│ │ │ └── utils.py
│ │ ├── preload.py
│ │ ├── requirements.txt
│ │ ├── scripts/
│ │ │ ├── controlnet.py
│ │ │ └── xyz_grid_support.py
│ │ └── style.css
│ ├── sd_forge_dynamic_thresholding/
│ │ ├── LICENSE.txt
│ │ ├── lib_dynamic_thresholding/
│ │ │ ├── dynthres.py
│ │ │ └── dynthres_core.py
│ │ └── scripts/
│ │ └── forge_dynamic_thresholding.py
│ ├── sd_forge_fooocus_inpaint/
│ │ └── scripts/
│ │ ├── fooocus_inpaint_head
│ │ └── forge_fooocus_inpaint.py
│ ├── sd_forge_freeu/
│ │ └── scripts/
│ │ └── forge_freeu.py
│ ├── sd_forge_ipadapter/
│ │ ├── LICENSE
│ │ ├── lib_ipadapter/
│ │ │ ├── IPAdapterPlus.py
│ │ │ └── resampler.py
│ │ ├── scripts/
│ │ │ └── forge_ipadapter.py
│ │ └── thanks
│ ├── sd_forge_kohya_hrfix/
│ │ └── scripts/
│ │ └── kohya_hrfix.py
│ ├── sd_forge_latent_modifier/
│ │ ├── LICENSE
│ │ ├── README.md
│ │ ├── lib_latent_modifier/
│ │ │ └── sampler_mega_modifier.py
│ │ └── scripts/
│ │ └── forge_latent_modifier.py
│ ├── sd_forge_lora/
│ │ ├── extra_networks_lora.py
│ │ ├── lora.py
│ │ ├── lora_logger.py
│ │ ├── network.py
│ │ ├── networks.py
│ │ ├── preload.py
│ │ ├── scripts/
│ │ │ └── lora_script.py
│ │ ├── ui_edit_user_metadata.py
│ │ └── ui_extra_networks_lora.py
│ ├── sd_forge_multidiffusion/
│ │ ├── lib_multidiffusion/
│ │ │ └── tiled_diffusion.py
│ │ └── scripts/
│ │ └── forge_multidiffusion.py
│ ├── sd_forge_neveroom/
│ │ └── scripts/
│ │ └── forge_never_oom.py
│ ├── sd_forge_perturbed_attention/
│ │ └── scripts/
│ │ └── forge_perturbed_attention.py
│ ├── sd_forge_sag/
│ │ └── scripts/
│ │ └── forge_sag.py
│ ├── sd_forge_stylealign/
│ │ └── scripts/
│ │ └── forge_stylealign.py
│ └── soft-inpainting/
│ └── scripts/
│ └── soft_inpainting.py
├── html/
│ ├── extra-networks-card.html
│ ├── extra-networks-copy-path-button.html
│ ├── extra-networks-edit-item-button.html
│ ├── extra-networks-metadata-button.html
│ ├── extra-networks-no-cards.html
│ ├── extra-networks-pane-dirs.html
│ ├── extra-networks-pane-tree.html
│ ├── extra-networks-pane.html
│ ├── extra-networks-tree-button.html
│ ├── footer.html
│ └── licenses.html
├── javascript/
│ ├── aspectRatioOverlay.js
│ ├── contextMenus.js
│ ├── dragdrop.js
│ ├── edit-attention.js
│ ├── edit-order.js
│ ├── extensions.js
│ ├── extraNetworks.js
│ ├── generationParams.js
│ ├── gradio.js
│ ├── hints.js
│ ├── hires_fix.js
│ ├── imageMaskFix.js
│ ├── imageviewer.js
│ ├── imageviewerGamepad.js
│ ├── inputAccordion.js
│ ├── localStorage.js
│ ├── localization.js
│ ├── notification.js
│ ├── profilerVisualization.js
│ ├── progressbar.js
│ ├── resizeHandle.js
│ ├── settings.js
│ ├── textualInversion.js
│ ├── token-counters.js
│ ├── ui.js
│ └── ui_settings_hints.js
├── k_diffusion/
│ ├── deis.py
│ ├── external.py
│ ├── sampling.py
│ └── utils.py
├── launch.py
├── localizations/
│ └── Put localization files here.txt
├── modules/
│ ├── api/
│ │ ├── api.py
│ │ └── models.py
│ ├── cache.py
│ ├── call_queue.py
│ ├── cmd_args.py
│ ├── codeformer_model.py
│ ├── config_states.py
│ ├── dat_model.py
│ ├── deepbooru.py
│ ├── deepbooru_model.py
│ ├── devices.py
│ ├── errors.py
│ ├── esrgan_model.py
│ ├── extensions.py
│ ├── extra_networks.py
│ ├── extra_networks_hypernet.py
│ ├── extras.py
│ ├── face_restoration.py
│ ├── face_restoration_utils.py
│ ├── fifo_lock.py
│ ├── gfpgan_model.py
│ ├── gitpython_hack.py
│ ├── gradio_extensions.py
│ ├── hashes.py
│ ├── hat_model.py
│ ├── hypernetworks/
│ │ ├── hypernetwork.py
│ │ └── ui.py
│ ├── images.py
│ ├── img2img.py
│ ├── import_hook.py
│ ├── infotext_utils.py
│ ├── infotext_versions.py
│ ├── initialize.py
│ ├── initialize_util.py
│ ├── interrogate.py
│ ├── launch_utils.py
│ ├── localization.py
│ ├── logging_config.py
│ ├── lowvram.py
│ ├── mac_specific.py
│ ├── masking.py
│ ├── memmon.py
│ ├── modelloader.py
│ ├── models/
│ │ ├── diffusion/
│ │ │ ├── ddpm_edit.py
│ │ │ └── uni_pc/
│ │ │ ├── __init__.py
│ │ │ ├── sampler.py
│ │ │ └── uni_pc.py
│ │ └── sd3/
│ │ ├── mmdit.py
│ │ ├── other_impls.py
│ │ ├── sd3_cond.py
│ │ ├── sd3_impls.py
│ │ └── sd3_model.py
│ ├── ngrok.py
│ ├── npu_specific.py
│ ├── options.py
│ ├── patches.py
│ ├── paths.py
│ ├── paths_internal.py
│ ├── postprocessing.py
│ ├── processing.py
│ ├── processing_scripts/
│ │ ├── comments.py
│ │ ├── refiner.py
│ │ ├── sampler.py
│ │ └── seed.py
│ ├── profiling.py
│ ├── progress.py
│ ├── prompt_parser.py
│ ├── realesrgan_model.py
│ ├── restart.py
│ ├── rng.py
│ ├── rng_philox.py
│ ├── safe.py
│ ├── script_callbacks.py
│ ├── script_loading.py
│ ├── scripts.py
│ ├── scripts_auto_postprocessing.py
│ ├── scripts_postprocessing.py
│ ├── sd_disable_initialization.py
│ ├── sd_emphasis.py
│ ├── sd_hijack.py
│ ├── sd_hijack_checkpoint.py
│ ├── sd_hijack_clip.py
│ ├── sd_hijack_clip_old.py
│ ├── sd_hijack_ip2p.py
│ ├── sd_hijack_open_clip.py
│ ├── sd_hijack_optimizations.py
│ ├── sd_hijack_unet.py
│ ├── sd_hijack_utils.py
│ ├── sd_hijack_xlmr.py
│ ├── sd_models.py
│ ├── sd_models_config.py
│ ├── sd_models_types.py
│ ├── sd_models_xl.py
│ ├── sd_samplers.py
│ ├── sd_samplers_cfg_denoiser.py
│ ├── sd_samplers_common.py
│ ├── sd_samplers_compvis.py
│ ├── sd_samplers_extra.py
│ ├── sd_samplers_kdiffusion.py
│ ├── sd_samplers_lcm.py
│ ├── sd_samplers_timesteps.py
│ ├── sd_samplers_timesteps_impl.py
│ ├── sd_schedulers.py
│ ├── sd_unet.py
│ ├── sd_vae.py
│ ├── sd_vae_approx.py
│ ├── sd_vae_taesd.py
│ ├── shared.py
│ ├── shared_cmd_options.py
│ ├── shared_gradio_themes.py
│ ├── shared_init.py
│ ├── shared_items.py
│ ├── shared_options.py
│ ├── shared_state.py
│ ├── shared_total_tqdm.py
│ ├── stealth_infotext.py
│ ├── styles.py
│ ├── sysinfo.py
│ ├── textual_inversion/
│ │ ├── autocrop.py
│ │ ├── image_embedding.py
│ │ ├── textual_inversion.py
│ │ └── ui.py
│ ├── timer.py
│ ├── torch_utils.py
│ ├── txt2img.py
│ ├── ui.py
│ ├── ui_checkpoint_merger.py
│ ├── ui_common.py
│ ├── ui_components.py
│ ├── ui_extensions.py
│ ├── ui_extra_networks.py
│ ├── ui_extra_networks_checkpoints.py
│ ├── ui_extra_networks_checkpoints_user_metadata.py
│ ├── ui_extra_networks_hypernets.py
│ ├── ui_extra_networks_textual_inversion.py
│ ├── ui_extra_networks_user_metadata.py
│ ├── ui_gradio_extensions.py
│ ├── ui_loadsave.py
│ ├── ui_postprocessing.py
│ ├── ui_prompt_styles.py
│ ├── ui_settings.py
│ ├── ui_tempdir.py
│ ├── ui_toprow.py
│ ├── upscaler.py
│ ├── upscaler_utils.py
│ ├── util.py
│ ├── xlmr.py
│ ├── xlmr_m18.py
│ └── xpu_specific.py
├── modules_forge/
│ ├── alter_samplers.py
│ ├── bnb_installer.py
│ ├── config.py
│ ├── cuda_malloc.py
│ ├── diffusers_patcher.py
│ ├── forge_canvas/
│ │ ├── canvas.css
│ │ ├── canvas.html
│ │ └── canvas.py
│ ├── forge_space.py
│ ├── forge_version.py
│ ├── gradio_compile.py
│ ├── initialization.py
│ ├── main_entry.py
│ ├── main_thread.py
│ ├── patch_basic.py
│ ├── shared.py
│ ├── shared_options.py
│ ├── supported_controlnet.py
│ ├── supported_preprocessor.py
│ └── utils.py
├── package.json
├── packages_3rdparty/
│ ├── README.md
│ ├── comfyui_lora_collection/
│ │ ├── LICENSE
│ │ ├── lora.py
│ │ └── utils.py
│ ├── gguf/
│ │ ├── LICENSE
│ │ ├── README.md
│ │ ├── __init__.py
│ │ ├── constants.py
│ │ ├── gguf_reader.py
│ │ ├── gguf_writer.py
│ │ ├── lazy.py
│ │ ├── metadata.py
│ │ ├── quants.py
│ │ ├── quick_4bits_ops.py
│ │ ├── tensor_mapping.py
│ │ ├── utility.py
│ │ └── vocab.py
│ └── webui_lora_collection/
│ ├── LICENSE.txt
│ ├── lora.py
│ ├── lyco_helpers.py
│ ├── network.py
│ ├── network_full.py
│ ├── network_glora.py
│ ├── network_hada.py
│ ├── network_ia3.py
│ ├── network_lokr.py
│ ├── network_lora.py
│ ├── network_norm.py
│ └── network_oft.py
├── pyproject.toml
├── requirements_versions.txt
├── script.js
├── scripts/
│ ├── custom_code.py
│ ├── img2imgalt.py
│ ├── loopback.py
│ ├── outpainting_mk_2.py
│ ├── poor_mans_outpainting.py
│ ├── postprocessing_codeformer.py
│ ├── postprocessing_focal_crop.py
│ ├── postprocessing_gfpgan.py
│ ├── postprocessing_upscale.py
│ ├── prompt_matrix.py
│ ├── prompts_from_file.py
│ ├── sd_upscale.py
│ └── xyz_grid.py
├── spaces.py
├── style.css
├── styles_integrated.csv
├── webui-macos-env.sh
├── webui.bat
├── webui.py
└── webui.sh
================================================
FILE CONTENTS
================================================
================================================
FILE: .eslintignore
================================================
extensions
extensions-disabled
extensions-builtin/sd_forge_controlnet
repositories
venv
================================================
FILE: .eslintrc.js
================================================
/* global module */
module.exports = {
env: {
browser: true,
es2021: true,
},
extends: "eslint:recommended",
parserOptions: {
ecmaVersion: "latest",
},
rules: {
"arrow-spacing": "error",
"block-spacing": "error",
"brace-style": "error",
"comma-dangle": ["error", "only-multiline"],
"comma-spacing": "error",
"comma-style": ["error", "last"],
"curly": ["error", "multi-line", "consistent"],
"eol-last": "error",
"func-call-spacing": "error",
"function-call-argument-newline": ["error", "consistent"],
"function-paren-newline": ["error", "consistent"],
"indent": ["error", 4],
"key-spacing": "error",
"keyword-spacing": "error",
"linebreak-style": ["error", "unix"],
"no-extra-semi": "error",
"no-mixed-spaces-and-tabs": "error",
"no-multi-spaces": "error",
"no-redeclare": ["error", {builtinGlobals: false}],
"no-trailing-spaces": "error",
"no-unused-vars": "off",
"no-whitespace-before-property": "error",
"object-curly-newline": ["error", {consistent: true, multiline: true}],
"object-curly-spacing": ["error", "never"],
"operator-linebreak": ["error", "after"],
"quote-props": ["error", "consistent-as-needed"],
"semi": ["error", "always"],
"semi-spacing": "error",
"semi-style": ["error", "last"],
"space-before-blocks": "error",
"space-before-function-paren": ["error", "never"],
"space-in-parens": ["error", "never"],
"space-infix-ops": "error",
"space-unary-ops": "error",
"switch-colon-spacing": "error",
"template-curly-spacing": ["error", "never"],
"unicode-bom": "error",
},
globals: {
//script.js
gradioApp: "readonly",
executeCallbacks: "readonly",
onAfterUiUpdate: "readonly",
onOptionsChanged: "readonly",
onUiLoaded: "readonly",
onUiUpdate: "readonly",
uiCurrentTab: "writable",
uiElementInSight: "readonly",
uiElementIsVisible: "readonly",
//ui.js
opts: "writable",
all_gallery_buttons: "readonly",
selected_gallery_button: "readonly",
selected_gallery_index: "readonly",
switch_to_txt2img: "readonly",
switch_to_img2img_tab: "readonly",
switch_to_img2img: "readonly",
switch_to_sketch: "readonly",
switch_to_inpaint: "readonly",
switch_to_inpaint_sketch: "readonly",
switch_to_extras: "readonly",
get_tab_index: "readonly",
create_submit_args: "readonly",
restart_reload: "readonly",
updateInput: "readonly",
onEdit: "readonly",
//extraNetworks.js
requestGet: "readonly",
popup: "readonly",
// profilerVisualization.js
createVisualizationTable: "readonly",
// from python
localization: "readonly",
// progrssbar.js
randomId: "readonly",
requestProgress: "readonly",
// imageviewer.js
modalPrevImage: "readonly",
modalNextImage: "readonly",
// localStorage.js
localSet: "readonly",
localGet: "readonly",
localRemove: "readonly",
// resizeHandle.js
setupResizeHandle: "writable"
}
};
================================================
FILE: .git-blame-ignore-revs
================================================
# Apply ESlint
9c54b78d9dde5601e916f308d9a9d6953ec39430
================================================
FILE: .gitignore
================================================
huggingface_space_mirror/
random_test.py
__pycache__
*.ckpt
*.safetensors
*.pth
*.dev.js
*_s.py
*_u.py
*_m.py
*_i.py
.DS_Store
/output/
/outputs/
/ESRGAN/*
/SwinIR/*
/repositories
/venv
/tmp
/output
/model.ckpt
/models/**/*
/GFPGANv1.3.pth
/gfpgan/weights/*.pth
/ui-config.json
/outputs
/config.json
/log
/webui.settings.bat
/embeddings
/styles.csv
/params.txt
/styles.csv.bak
/webui-user.bat
/webui-user.sh
/interrogate
/user.css
/.idea
notification.mp3
/SwinIR
/textual_inversion
.vscode
/extensions
/test/stdout.txt
/test/stderr.txt
/cache.json*
/config_states/
/node_modules
/package-lock.json
/.coverage*
/test/test_outputs
/cache
trace.json
/sysinfo-????-??-??-??-??.json
/test/results.xml
coverage.xml
**/tests/**/expectations
================================================
FILE: .pylintrc
================================================
# See https://pylint.pycqa.org/en/latest/user_guide/messages/message_control.html
[MESSAGES CONTROL]
disable=C,R,W,E,I
================================================
FILE: CHANGELOG.md
================================================
## 1.10.1
### Bug Fixes:
* fix image upscale on cpu ([#16275](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16275))
## 1.10.0
### Features:
* A lot of performance improvements (see below in Performance section)
* Stable Diffusion 3 support ([#16030](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16030), [#16164](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16164), [#16212](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16212))
* Recommended Euler sampler; DDIM and other timestamp samplers currently not supported
* T5 text model is disabled by default, enable it in settings
* New schedulers:
* Align Your Steps ([#15751](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15751))
* KL Optimal ([#15608](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15608))
* Normal ([#16149](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16149))
* DDIM ([#16149](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16149))
* Simple ([#16142](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16142))
* Beta ([#16235](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16235))
* New sampler: DDIM CFG++ ([#16035](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16035))
### Minor:
* Option to skip CFG on early steps ([#15607](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15607))
* Add --models-dir option ([#15742](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15742))
* Allow mobile users to open context menu by using two fingers press ([#15682](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15682))
* Infotext: add Lora name as TI hashes for bundled Textual Inversion ([#15679](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15679))
* Check model's hash after downloading it to prevent corruped downloads ([#15602](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15602))
* More extension tag filtering options ([#15627](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15627))
* When saving AVIF, use JPEG's quality setting ([#15610](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15610))
* Add filename pattern: `[basename]` ([#15978](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15978))
* Add option to enable clip skip for clip L on SDXL ([#15992](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15992))
* Option to prevent screen sleep during generation ([#16001](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16001))
* ToggleLivePriview button in image viewer ([#16065](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16065))
* Remove ui flashing on reloading and fast scrollong ([#16153](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16153))
* option to disable save button log.csv ([#16242](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16242))
### Extensions and API:
* Add process_before_every_sampling hook ([#15984](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15984))
* Return HTTP 400 instead of 404 on invalid sampler error ([#16140](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16140))
### Performance:
* [Performance 1/6] use_checkpoint = False ([#15803](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15803))
* [Performance 2/6] Replace einops.rearrange with torch native ops ([#15804](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15804))
* [Performance 4/6] Precompute is_sdxl_inpaint flag ([#15806](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15806))
* [Performance 5/6] Prevent unnecessary extra networks bias backup ([#15816](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15816))
* [Performance 6/6] Add --precision half option to avoid casting during inference ([#15820](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15820))
* [Performance] LDM optimization patches ([#15824](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15824))
* [Performance] Keep sigmas on CPU ([#15823](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15823))
* Check for nans in unet only once, after all steps have been completed
* Added pption to run torch profiler for image generation
### Bug Fixes:
* Fix for grids without comprehensive infotexts ([#15958](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15958))
* feat: lora partial update precede full update ([#15943](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15943))
* Fix bug where file extension had an extra '.' under some circumstances ([#15893](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15893))
* Fix corrupt model initial load loop ([#15600](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15600))
* Allow old sampler names in API ([#15656](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15656))
* more old sampler scheduler compatibility ([#15681](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15681))
* Fix Hypertile xyz ([#15831](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15831))
* XYZ CSV skipinitialspace ([#15832](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15832))
* fix soft inpainting on mps and xpu, torch_utils.float64 ([#15815](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15815))
* fix extention update when not on main branch ([#15797](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15797))
* update pickle safe filenames
* use relative path for webui-assets css ([#15757](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15757))
* When creating a virtual environment, upgrade pip in webui.bat/webui.sh ([#15750](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15750))
* Fix AttributeError ([#15738](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15738))
* use script_path for webui root in launch_utils ([#15705](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15705))
* fix extra batch mode P Transparency ([#15664](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15664))
* use gradio theme colors in css ([#15680](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15680))
* Fix dragging text within prompt input ([#15657](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15657))
* Add correct mimetype for .mjs files ([#15654](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15654))
* QOL Items - handle metadata issues more cleanly for SD models, Loras and embeddings ([#15632](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15632))
* replace wsl-open with wslpath and explorer.exe ([#15968](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15968))
* Fix SDXL Inpaint ([#15976](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15976))
* multi size grid ([#15988](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15988))
* fix Replace preview ([#16118](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16118))
* Possible fix of wrong scale in weight decomposition ([#16151](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16151))
* Ensure use of python from venv on Mac and Linux ([#16116](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16116))
* Prioritize python3.10 over python3 if both are available on Linux and Mac (with fallback) ([#16092](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16092))
* stoping generation extras ([#16085](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16085))
* Fix SD2 loading ([#16078](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16078), [#16079](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16079))
* fix infotext Lora hashes for hires fix different lora ([#16062](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16062))
* Fix sampler scheduler autocorrection warning ([#16054](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16054))
* fix ui flashing on reloading and fast scrollong ([#16153](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16153))
* fix upscale logic ([#16239](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16239))
* [bug] do not break progressbar on non-job actions (add wrap_gradio_call_no_job) ([#16202](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16202))
* fix OSError: cannot write mode P as JPEG ([#16194](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16194))
### Other:
* fix changelog #15883 -> #15882 ([#15907](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15907))
* ReloadUI backgroundColor --background-fill-primary ([#15864](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15864))
* Use different torch versions for Intel and ARM Macs ([#15851](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15851))
* XYZ override rework ([#15836](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15836))
* scroll extensions table on overflow ([#15830](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15830))
* img2img batch upload method ([#15817](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15817))
* chore: sync v1.8.0 packages according to changelog ([#15783](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15783))
* Add AVIF MIME type support to mimetype definitions ([#15739](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15739))
* Update imageviewer.js ([#15730](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15730))
* no-referrer ([#15641](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15641))
* .gitignore trace.json ([#15980](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15980))
* Bump spandrel to 0.3.4 ([#16144](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16144))
* Defunct --max-batch-count ([#16119](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16119))
* docs: update bug_report.yml ([#16102](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16102))
* Maintaining Project Compatibility for Python 3.9 Users Without Upgrade Requirements. ([#16088](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16088), [#16169](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16169), [#16192](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16192))
* Update torch for ARM Macs to 2.3.1 ([#16059](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16059))
* remove deprecated setting dont_fix_second_order_samplers_schedule ([#16061](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16061))
* chore: fix typos ([#16060](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16060))
* shlex.join launch args in console log ([#16170](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16170))
* activate venv .bat ([#16231](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16231))
* add ids to the resize tabs in img2img ([#16218](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16218))
* update installation guide linux ([#16178](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16178))
* Robust sysinfo ([#16173](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16173))
* do not send image size on paste inpaint ([#16180](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16180))
* Fix noisy DS_Store files for MacOS ([#16166](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16166))
## 1.9.4
### Bug Fixes:
* pin setuptools version to fix the startup error ([#15882](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15882))
## 1.9.3
### Bug Fixes:
* fix get_crop_region_v2 ([#15594](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15594))
## 1.9.2
### Extensions and API:
* restore 1.8.0-style naming of scripts
## 1.9.1
### Minor:
* Add avif support ([#15582](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15582))
* Add filename patterns: `[sampler_scheduler]` and `[scheduler]` ([#15581](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15581))
### Extensions and API:
* undo adding scripts to sys.modules
* Add schedulers API endpoint ([#15577](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15577))
* Remove API upscaling factor limits ([#15560](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15560))
### Bug Fixes:
* Fix images do not match / Coordinate 'right' is less than 'left' ([#15534](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15534))
* fix: remove_callbacks_for_function should also remove from the ordered map ([#15533](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15533))
* fix x1 upscalers ([#15555](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15555))
* Fix cls.__module__ value in extension script ([#15532](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15532))
* fix typo in function call (eror -> error) ([#15531](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15531))
### Other:
* Hide 'No Image data blocks found.' message ([#15567](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15567))
* Allow webui.sh to be runnable from arbitrary directories containing a .git file ([#15561](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15561))
* Compatibility with Debian 11, Fedora 34+ and openSUSE 15.4+ ([#15544](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15544))
* numpy DeprecationWarning product -> prod ([#15547](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15547))
* get_crop_region_v2 ([#15583](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15583), [#15587](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15587))
## 1.9.0
### Features:
* Make refiner switchover based on model timesteps instead of sampling steps ([#14978](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14978))
* add an option to have old-style directory view instead of tree view; stylistic changes for extra network sorting/search controls
* add UI for reordering callbacks, support for specifying callback order in extension metadata ([#15205](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15205))
* Sgm uniform scheduler for SDXL-Lightning models ([#15325](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15325))
* Scheduler selection in main UI ([#15333](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15333), [#15361](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15361), [#15394](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15394))
### Minor:
* "open images directory" button now opens the actual dir ([#14947](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14947))
* Support inference with LyCORIS BOFT networks ([#14871](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14871), [#14973](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14973))
* make extra network card description plaintext by default, with an option to re-enable HTML as it was
* resize handle for extra networks ([#15041](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15041))
* cmd args: `--unix-filenames-sanitization` and `--filenames-max-length` ([#15031](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15031))
* show extra networks parameters in HTML table rather than raw JSON ([#15131](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15131))
* Add DoRA (weight-decompose) support for LoRA/LoHa/LoKr ([#15160](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15160), [#15283](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15283))
* Add '--no-prompt-history' cmd args for disable last generation prompt history ([#15189](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15189))
* update preview on Replace Preview ([#15201](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15201))
* only fetch updates for extensions' active git branches ([#15233](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15233))
* put upscale postprocessing UI into an accordion ([#15223](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15223))
* Support dragdrop for URLs to read infotext ([#15262](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15262))
* use diskcache library for caching ([#15287](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15287), [#15299](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15299))
* Allow PNG-RGBA for Extras Tab ([#15334](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15334))
* Support cover images embedded in safetensors metadata ([#15319](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15319))
* faster interrupt when using NN upscale ([#15380](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15380))
* Extras upscaler: an input field to limit maximul side length for the output image ([#15293](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15293), [#15415](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15415), [#15417](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15417), [#15425](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15425))
* add an option to hide postprocessing options in Extras tab
### Extensions and API:
* ResizeHandleRow - allow overriden column scale parametr ([#15004](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15004))
* call script_callbacks.ui_settings_callback earlier; fix extra-options-section built-in extension killing the ui if using a setting that doesn't exist
* make it possible to use zoom.js outside webui context ([#15286](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15286), [#15288](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15288))
* allow variants for extension name in metadata.ini ([#15290](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15290))
* make reloading UI scripts optional when doing Reload UI, and off by default
* put request: gr.Request at start of img2img function similar to txt2img
* open_folder as util ([#15442](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15442))
* make it possible to import extensions' script files as `import scripts.<filename>` ([#15423](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15423))
### Performance:
* performance optimization for extra networks HTML pages
* optimization for extra networks filtering
* optimization for extra networks sorting
### Bug Fixes:
* prevent escape button causing an interrupt when no generation has been made yet
* [bug] avoid doble upscaling in inpaint ([#14966](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14966))
* possible fix for reload button not appearing in some cases for extra networks.
* fix: the `split_threshold` parameter does not work when running Split oversized images ([#15006](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15006))
* Fix resize-handle visability for vertical layout (mobile) ([#15010](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15010))
* register_tmp_file also for mtime ([#15012](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15012))
* Protect alphas_cumprod during refiner switchover ([#14979](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14979))
* Fix EXIF orientation in API image loading ([#15062](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15062))
* Only override emphasis if actually used in prompt ([#15141](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15141))
* Fix emphasis infotext missing from `params.txt` ([#15142](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15142))
* fix extract_style_text_from_prompt #15132 ([#15135](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15135))
* Fix Soft Inpaint for AnimateDiff ([#15148](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15148))
* edit-attention: deselect surrounding whitespace ([#15178](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15178))
* chore: fix font not loaded ([#15183](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15183))
* use natural sort in extra networks when ordering by path
* Fix built-in lora system bugs caused by torch.nn.MultiheadAttention ([#15190](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15190))
* Avoid error from None in get_learned_conditioning ([#15191](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15191))
* Add entry to MassFileLister after writing metadata ([#15199](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15199))
* fix issue with Styles when Hires prompt is used ([#15269](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15269), [#15276](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15276))
* Strip comments from hires fix prompt ([#15263](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15263))
* Make imageviewer event listeners browser consistent ([#15261](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15261))
* Fix AttributeError in OFT when trying to get MultiheadAttention weight ([#15260](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15260))
* Add missing .mean() back ([#15239](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15239))
* fix "Restore progress" button ([#15221](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15221))
* fix ui-config for InputAccordion [custom_script_source] ([#15231](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15231))
* handle 0 wheel deltaY ([#15268](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15268))
* prevent alt menu for firefox ([#15267](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15267))
* fix: fix syntax errors ([#15179](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15179))
* restore outputs path ([#15307](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15307))
* Escape btn_copy_path filename ([#15316](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15316))
* Fix extra networks buttons when filename contains an apostrophe ([#15331](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15331))
* escape brackets in lora random prompt generator ([#15343](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15343))
* fix: Python version check for PyTorch installation compatibility ([#15390](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15390))
* fix typo in call_queue.py ([#15386](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15386))
* fix: when find already_loaded model, remove loaded by array index ([#15382](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15382))
* minor bug fix of sd model memory management ([#15350](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15350))
* Fix CodeFormer weight ([#15414](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15414))
* Fix: Remove script callbacks in ordered_callbacks_map ([#15428](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15428))
* fix limited file write (thanks, Sylwia)
* Fix extra-single-image API not doing upscale failed ([#15465](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15465))
* error handling paste_field callables ([#15470](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15470))
### Hardware:
* Add training support and change lspci for Ascend NPU ([#14981](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14981))
* Update to ROCm5.7 and PyTorch ([#14820](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14820))
* Better workaround for Navi1, removing --pre for Navi3 ([#15224](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15224))
* Ascend NPU wiki page ([#15228](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15228))
### Other:
* Update comment for Pad prompt/negative prompt v0 to add a warning about truncation, make it override the v1 implementation
* support resizable columns for touch (tablets) ([#15002](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15002))
* Fix #14591 using translated content to do categories mapping ([#14995](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14995))
* Use `absolute` path for normalized filepath ([#15035](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15035))
* resizeHandle handle double tap ([#15065](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15065))
* --dat-models-path cmd flag ([#15039](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15039))
* Add a direct link to the binary release ([#15059](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15059))
* upscaler_utils: Reduce logging ([#15084](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15084))
* Fix various typos with crate-ci/typos ([#15116](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15116))
* fix_jpeg_live_preview ([#15102](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15102))
* [alternative fix] can't load webui if selected wrong extra option in ui ([#15121](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15121))
* Error handling for unsupported transparency ([#14958](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14958))
* Add model description to searched terms ([#15198](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15198))
* bump action version ([#15272](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15272))
* PEP 604 annotations ([#15259](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15259))
* Automatically Set the Scale by value when user selects an Upscale Model ([#15244](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15244))
* move postprocessing-for-training into builtin extensions ([#15222](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15222))
* type hinting in shared.py ([#15211](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15211))
* update ruff to 0.3.3
* Update pytorch lightning utilities ([#15310](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15310))
* Add Size as an XYZ Grid option ([#15354](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15354))
* Use HF_ENDPOINT variable for HuggingFace domain with default ([#15443](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15443))
* re-add update_file_entry ([#15446](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15446))
* create_infotext allow index and callable, re-work Hires prompt infotext ([#15460](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15460))
* update restricted_opts to include more options for --hide-ui-dir-config ([#15492](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15492))
## 1.8.0
### Features:
* Update torch to version 2.1.2
* Soft Inpainting ([#14208](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14208))
* FP8 support ([#14031](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14031), [#14327](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14327))
* Support for SDXL-Inpaint Model ([#14390](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14390))
* Use Spandrel for upscaling and face restoration architectures ([#14425](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14425), [#14467](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14467), [#14473](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14473), [#14474](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14474), [#14477](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14477), [#14476](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14476), [#14484](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14484), [#14500](https://github.com/AUTOMATIC1111/stable-difusion-webui/pull/14500), [#14501](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14501), [#14504](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14504), [#14524](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14524), [#14809](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14809))
* Automatic backwards version compatibility (when loading infotexts from old images with program version specified, will add compatibility settings)
* Implement zero terminal SNR noise schedule option (**[SEED BREAKING CHANGE](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Seed-breaking-changes#180-dev-170-225-2024-01-01---zero-terminal-snr-noise-schedule-option)**, [#14145](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14145), [#14979](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14979))
* Add a [✨] button to run hires fix on selected image in the gallery (with help from [#14598](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14598), [#14626](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14626), [#14728](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14728))
* [Separate assets repository](https://github.com/AUTOMATIC1111/stable-diffusion-webui-assets); serve fonts locally rather than from google's servers
* Official LCM Sampler Support ([#14583](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14583))
* Add support for DAT upscaler models ([#14690](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14690), [#15039](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15039))
* Extra Networks Tree View ([#14588](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14588), [#14900](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14900))
* NPU Support ([#14801](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14801))
* Prompt comments support
### Minor:
* Allow pasting in WIDTHxHEIGHT strings into the width/height fields ([#14296](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14296))
* add option: Live preview in full page image viewer ([#14230](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14230), [#14307](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14307))
* Add keyboard shortcuts for generate/skip/interrupt ([#14269](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14269))
* Better TCMALLOC support on different platforms ([#14227](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14227), [#14883](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14883), [#14910](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14910))
* Lora not found warning ([#14464](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14464))
* Adding negative prompts to Loras in extra networks ([#14475](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14475))
* xyz_grid: allow varying the seed along an axis separate from axis options ([#12180](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12180))
* option to convert VAE to bfloat16 (implementation of [#9295](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9295))
* Better IPEX support ([#14229](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14229), [#14353](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14353), [#14559](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14559), [#14562](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14562), [#14597](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14597))
* Option to interrupt after current generation rather than immediately ([#13653](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13653), [#14659](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14659))
* Fullscreen Preview control fading/disable ([#14291](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14291))
* Finer settings freezing control ([#13789](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13789))
* Increase Upscaler Limits ([#14589](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14589))
* Adjust brush size with hotkeys ([#14638](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14638))
* Add checkpoint info to csv log file when saving images ([#14663](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14663))
* Make more columns resizable ([#14740](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14740), [#14884](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14884))
* Add an option to not overlay original image for inpainting for #14727
* Add Pad conds v0 option to support same generation with DDIM as before 1.6.0
* Add "Interrupting..." placeholder.
* Button for refresh extensions list ([#14857](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14857))
* Add an option to disable normalization after calculating emphasis. ([#14874](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14874))
* When counting tokens, also include enabled styles (can be disabled in settings to revert to previous behavior)
* Configuration for the [📂] button for image gallery ([#14947](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14947))
* Support inference with LyCORIS BOFT networks ([#14871](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14871), [#14973](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14973))
* support resizable columns for touch (tablets) ([#15002](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15002))
### Extensions and API:
* Removed packages from requirements: basicsr, gfpgan, realesrgan; as well as their dependencies: absl-py, addict, beautifulsoup4, future, gdown, grpcio, importlib-metadata, lmdb, lpips, Markdown, platformdirs, PySocks, soupsieve, tb-nightly, tensorboard-data-server, tomli, Werkzeug, yapf, zipp, soupsieve
* Enable task ids for API ([#14314](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14314))
* add override_settings support for infotext API
* rename generation_parameters_copypaste module to infotext_utils
* prevent crash due to Script __init__ exception ([#14407](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14407))
* Bump numpy to 1.26.2 ([#14471](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14471))
* Add utility to inspect a model's dtype/device ([#14478](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14478))
* Implement general forward method for all method in built-in lora ext ([#14547](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14547))
* Execute model_loaded_callback after moving to target device ([#14563](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14563))
* Add self to CFGDenoiserParams ([#14573](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14573))
* Allow TLS with API only mode (--nowebui) ([#14593](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14593))
* New callback: postprocess_image_after_composite ([#14657](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14657))
* modules/api/api.py: add api endpoint to refresh embeddings list ([#14715](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14715))
* set_named_arg ([#14773](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14773))
* add before_token_counter callback and use it for prompt comments
* ResizeHandleRow - allow overridden column scale parameter ([#15004](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15004))
### Performance:
* Massive performance improvement for extra networks directories with a huge number of files in them in an attempt to tackle #14507 ([#14528](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14528))
* Reduce unnecessary re-indexing extra networks directory ([#14512](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14512))
* Avoid unnecessary `isfile`/`exists` calls ([#14527](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14527))
### Bug Fixes:
* fix multiple bugs related to styles multi-file support ([#14203](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14203), [#14276](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14276), [#14707](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14707))
* Lora fixes ([#14300](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14300), [#14237](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14237), [#14546](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14546), [#14726](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14726))
* Re-add setting lost as part of e294e46 ([#14266](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14266))
* fix extras caption BLIP ([#14330](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14330))
* include infotext into saved init image for img2img ([#14452](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14452))
* xyz grid handle axis_type is None ([#14394](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14394))
* Update Added (Fixed) IPV6 Functionality When there is No Webui Argument Passed webui.py ([#14354](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14354))
* fix API thread safe issues of txt2img and img2img ([#14421](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14421))
* handle selectable script_index is None ([#14487](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14487))
* handle config.json failed to load ([#14525](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14525), [#14767](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14767))
* paste infotext cast int as float ([#14523](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14523))
* Ensure GRADIO_ANALYTICS_ENABLED is set early enough ([#14537](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14537))
* Fix logging configuration again ([#14538](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14538))
* Handle CondFunc exception when resolving attributes ([#14560](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14560))
* Fix extras big batch crashes ([#14699](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14699))
* Fix using wrong model caused by alias ([#14655](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14655))
* Add # to the invalid_filename_chars list ([#14640](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14640))
* Fix extension check for requirements ([#14639](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14639))
* Fix tab indexes are reset after restart UI ([#14637](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14637))
* Fix nested manual cast ([#14689](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14689))
* Keep postprocessing upscale selected tab after restart ([#14702](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14702))
* XYZ grid: filter out blank vals when axis is int or float type (like int axis seed) ([#14754](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14754))
* fix CLIP Interrogator topN regex ([#14775](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14775))
* Fix dtype error in MHA layer/change dtype checking mechanism for manual cast ([#14791](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14791))
* catch load style.csv error ([#14814](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14814))
* fix error when editing extra networks card
* fix extra networks metadata failing to work properly when you create the .json file with metadata for the first time.
* util.walk_files extensions case insensitive ([#14879](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14879))
* if extensions page not loaded, prevent apply ([#14873](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14873))
* call the right function for token counter in img2img
* Fix the bugs that search/reload will disappear when using other ExtraNetworks extensions ([#14939](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14939))
* Gracefully handle mtime read exception from cache ([#14933](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14933))
* Only trigger interrupt on `Esc` when interrupt button visible ([#14932](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14932))
* Disable prompt token counters option actually disables token counting rather than just hiding results.
* avoid double upscaling in inpaint ([#14966](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14966))
* Fix #14591 using translated content to do categories mapping ([#14995](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14995))
* fix: the `split_threshold` parameter does not work when running Split oversized images ([#15006](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15006))
* Fix resize-handle for mobile ([#15010](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15010), [#15065](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15065))
### Other:
* Assign id for "extra_options". Replace numeric field with slider. ([#14270](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14270))
* change state dict comparison to ref compare ([#14216](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14216))
* Bump torch-rocm to 5.6/5.7 ([#14293](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14293))
* Base output path off data path ([#14446](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14446))
* reorder training preprocessing modules in extras tab ([#14367](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14367))
* Remove `cleanup_models` code ([#14472](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14472))
* only rewrite ui-config when there is change ([#14352](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14352))
* Fix lint issue from 501993eb ([#14495](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14495))
* Update README.md ([#14548](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14548))
* hires button, fix seeds ()
* Logging: set formatter correctly for fallback logger too ([#14618](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14618))
* Read generation info from infotexts rather than json for internal needs (save, extract seed from generated pic) ([#14645](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14645))
* improve get_crop_region ([#14709](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14709))
* Bump safetensors' version to 0.4.2 ([#14782](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14782))
* add tooltip create_submit_box ([#14803](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14803))
* extensions tab table row hover highlight ([#14885](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14885))
* Always add timestamp to displayed image ([#14890](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14890))
* Added core.filemode=false so doesn't track changes in file permission… ([#14930](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14930))
* Normalize command-line argument paths ([#14934](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14934), [#15035](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15035))
* Use original App Title in progress bar ([#14916](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14916))
* register_tmp_file also for mtime ([#15012](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15012))
## 1.7.0
### Features:
* settings tab rework: add search field, add categories, split UI settings page into many
* add altdiffusion-m18 support ([#13364](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13364))
* support inference with LyCORIS GLora networks ([#13610](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13610))
* add lora-embedding bundle system ([#13568](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13568))
* option to move prompt from top row into generation parameters
* add support for SSD-1B ([#13865](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13865))
* support inference with OFT networks ([#13692](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13692))
* script metadata and DAG sorting mechanism ([#13944](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13944))
* support HyperTile optimization ([#13948](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13948))
* add support for SD 2.1 Turbo ([#14170](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14170))
* remove Train->Preprocessing tab and put all its functionality into Extras tab
* initial IPEX support for Intel Arc GPU ([#14171](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14171))
### Minor:
* allow reading model hash from images in img2img batch mode ([#12767](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12767))
* add option to align with sgm repo's sampling implementation ([#12818](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12818))
* extra field for lora metadata viewer: `ss_output_name` ([#12838](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12838))
* add action in settings page to calculate all SD checkpoint hashes ([#12909](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12909))
* add button to copy prompt to style editor ([#12975](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12975))
* add --skip-load-model-at-start option ([#13253](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13253))
* write infotext to gif images
* read infotext from gif images ([#13068](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13068))
* allow configuring the initial state of InputAccordion in ui-config.json ([#13189](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13189))
* allow editing whitespace delimiters for ctrl+up/ctrl+down prompt editing ([#13444](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13444))
* prevent accidentally closing popup dialogs ([#13480](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13480))
* added option to play notification sound or not ([#13631](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13631))
* show the preview image in the full screen image viewer if available ([#13459](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13459))
* support for webui.settings.bat ([#13638](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13638))
* add an option to not print stack traces on ctrl+c
* start/restart generation by Ctrl (Alt) + Enter ([#13644](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13644))
* update prompts_from_file script to allow concatenating entries with the general prompt ([#13733](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13733))
* added a visible checkbox to input accordion
* added an option to hide all txt2img/img2img parameters in an accordion ([#13826](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13826))
* added 'Path' sorting option for Extra network cards ([#13968](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13968))
* enable prompt hotkeys in style editor ([#13931](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13931))
* option to show batch img2img results in UI ([#14009](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14009))
* infotext updates: add option to disregard certain infotext fields, add option to not include VAE in infotext, add explanation to infotext settings page, move some options to infotext settings page
* add FP32 fallback support on sd_vae_approx ([#14046](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046))
* support XYZ scripts / split hires path from unet ([#14126](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14126))
* allow use of multiple styles csv files ([#14125](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14125))
* make extra network card description plaintext by default, with an option (Treat card description as HTML) to re-enable HTML as it was (originally by [#13241](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13241))
### Extensions and API:
* update gradio to 3.41.2
* support installed extensions list api ([#12774](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12774))
* update pnginfo API to return dict with parsed values
* add noisy latent to `ExtraNoiseParams` for callback ([#12856](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12856))
* show extension datetime in UTC ([#12864](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12864), [#12865](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12865), [#13281](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13281))
* add an option to choose how to combine hires fix and refiner
* include program version in info response. ([#13135](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13135))
* sd_unet support for SDXL
* patch DDPM.register_betas so that users can put given_betas in model yaml ([#13276](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13276))
* xyz_grid: add prepare ([#13266](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13266))
* allow multiple localization files with same language in extensions ([#13077](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13077))
* add onEdit function for js and rework token-counter.js to use it
* fix the key error exception when processing override_settings keys ([#13567](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13567))
* ability for extensions to return custom data via api in response.images ([#13463](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13463))
* call state.jobnext() before postproces*() ([#13762](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13762))
* add option to set notification sound volume ([#13884](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13884))
* update Ruff to 0.1.6 ([#14059](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14059))
* add Block component creation callback ([#14119](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14119))
* catch uncaught exception with ui creation scripts ([#14120](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14120))
* use extension name for determining an extension is installed in the index ([#14063](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14063))
* update is_installed() from launch_utils.py to fix reinstalling already installed packages ([#14192](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14192))
### Bug Fixes:
* fix pix2pix producing bad results
* fix defaults settings page breaking when any of main UI tabs are hidden
* fix error that causes some extra networks to be disabled if both <lora:> and <lyco:> are present in the prompt
* fix for Reload UI function: if you reload UI on one tab, other opened tabs will no longer stop working
* prevent duplicate resize handler ([#12795](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12795))
* small typo: vae resolve bug ([#12797](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12797))
* hide broken image crop tool ([#12792](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12792))
* don't show hidden samplers in dropdown for XYZ script ([#12780](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12780))
* fix style editing dialog breaking if it's opened in both img2img and txt2img tabs
* hide --gradio-auth and --api-auth values from /internal/sysinfo report
* add missing infotext for RNG in options ([#12819](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12819))
* fix notification not playing when built-in webui tab is inactive ([#12834](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12834))
* honor `--skip-install` for extension installers ([#12832](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12832))
* don't print blank stdout in extension installers ([#12833](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12833), [#12855](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12855))
* get progressbar to display correctly in extensions tab
* keep order in list of checkpoints when loading model that doesn't have a checksum
* fix inpainting models in txt2img creating black pictures
* fix generation params regex ([#12876](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12876))
* fix batch img2img output dir with script ([#12926](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12926))
* fix #13080 - Hypernetwork/TI preview generation ([#13084](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13084))
* fix bug with sigma min/max overrides. ([#12995](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12995))
* more accurate check for enabling cuDNN benchmark on 16XX cards ([#12924](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12924))
* don't use multicond parser for negative prompt counter ([#13118](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13118))
* fix data-sort-name containing spaces ([#13412](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13412))
* update card on correct tab when editing metadata ([#13411](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13411))
* fix viewing/editing metadata when filename contains an apostrophe ([#13395](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13395))
* fix: --sd_model in "Prompts from file or textbox" script is not working ([#13302](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13302))
* better Support for Portable Git ([#13231](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13231))
* fix issues when webui_dir is not work_dir ([#13210](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13210))
* fix: lora-bias-backup don't reset cache ([#13178](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13178))
* account for customizable extra network separators whyen removing extra network text from the prompt ([#12877](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12877))
* re fix batch img2img output dir with script ([#13170](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13170))
* fix `--ckpt-dir` path separator and option use `short name` for checkpoint dropdown ([#13139](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13139))
* consolidated allowed preview formats, Fix extra network `.gif` not woking as preview ([#13121](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13121))
* fix venv_dir=- environment variable not working as expected on linux ([#13469](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13469))
* repair unload sd checkpoint button
* edit-attention fixes ([#13533](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13533))
* fix bug when using --gfpgan-models-path ([#13718](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13718))
* properly apply sort order for extra network cards when selected from dropdown
* fixes generation restart not working for some users when 'Ctrl+Enter' is pressed ([#13962](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13962))
* thread safe extra network list_items ([#13014](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13014))
* fix not able to exit metadata popup when pop up is too big ([#14156](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14156))
* fix auto focal point crop for opencv >= 4.8 ([#14121](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14121))
* make 'use-cpu all' actually apply to 'all' ([#14131](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14131))
* extras tab batch: actually use original filename
* make webui not crash when running with --disable-all-extensions option
### Other:
* non-local condition ([#12814](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12814))
* fix minor typos ([#12827](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12827))
* remove xformers Python version check ([#12842](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12842))
* style: file-metadata word-break ([#12837](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12837))
* revert SGM noise multiplier change for img2img because it breaks hires fix
* do not change quicksettings dropdown option when value returned is `None` ([#12854](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12854))
* [RC 1.6.0 - zoom is partly hidden] Update style.css ([#12839](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12839))
* chore: change extension time format ([#12851](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12851))
* WEBUI.SH - Use torch 2.1.0 release candidate for Navi 3 ([#12929](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12929))
* add Fallback at images.read_info_from_image if exif data was invalid ([#13028](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13028))
* update cmd arg description ([#12986](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12986))
* fix: update shared.opts.data when add_option ([#12957](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12957), [#13213](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13213))
* restore missing tooltips ([#12976](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12976))
* use default dropdown padding on mobile ([#12880](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12880))
* put enable console prompts option into settings from commandline args ([#13119](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13119))
* fix some deprecated types ([#12846](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12846))
* bump to torchsde==0.2.6 ([#13418](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13418))
* update dragdrop.js ([#13372](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13372))
* use orderdict as lru cache:opt/bug ([#13313](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13313))
* XYZ if not include sub grids do not save sub grid ([#13282](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13282))
* initialize state.time_start befroe state.job_count ([#13229](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13229))
* fix fieldname regex ([#13458](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13458))
* change denoising_strength default to None. ([#13466](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13466))
* fix regression ([#13475](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13475))
* fix IndexError ([#13630](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13630))
* fix: checkpoints_loaded:{checkpoint:state_dict}, model.load_state_dict issue in dict value empty ([#13535](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13535))
* update bug_report.yml ([#12991](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12991))
* requirements_versions httpx==0.24.1 ([#13839](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13839))
* fix parenthesis auto selection ([#13829](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13829))
* fix #13796 ([#13797](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13797))
* corrected a typo in `modules/cmd_args.py` ([#13855](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13855))
* feat: fix randn found element of type float at pos 2 ([#14004](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14004))
* adds tqdm handler to logging_config.py for progress bar integration ([#13996](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13996))
* hotfix: call shared.state.end() after postprocessing done ([#13977](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13977))
* fix dependency address patch 1 ([#13929](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13929))
* save sysinfo as .json ([#14035](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14035))
* move exception_records related methods to errors.py ([#14084](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14084))
* compatibility ([#13936](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13936))
* json.dump(ensure_ascii=False) ([#14108](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14108))
* dir buttons start with / so only the correct dir will be shown and no… ([#13957](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13957))
* alternate implementation for unet forward replacement that does not depend on hijack being applied
* re-add `keyedit_delimiters_whitespace` setting lost as part of commit e294e46 ([#14178](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14178))
* fix `save_samples` being checked early when saving masked composite ([#14177](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14177))
* slight optimization for mask and mask_composite ([#14181](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14181))
* add import_hook hack to work around basicsr/torchvision incompatibility ([#14186](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14186))
## 1.6.1
### Bug Fixes:
* fix an error causing the webui to fail to start ([#13839](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13839))
## 1.6.0
### Features:
* refiner support [#12371](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12371)
* add NV option for Random number generator source setting, which allows to generate same pictures on CPU/AMD/Mac as on NVidia videocards
* add style editor dialog
* hires fix: add an option to use a different checkpoint for second pass ([#12181](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12181))
* option to keep multiple loaded models in memory ([#12227](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12227))
* new samplers: Restart, DPM++ 2M SDE Exponential, DPM++ 2M SDE Heun, DPM++ 2M SDE Heun Karras, DPM++ 2M SDE Heun Exponential, DPM++ 3M SDE, DPM++ 3M SDE Karras, DPM++ 3M SDE Exponential ([#12300](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12300), [#12519](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12519), [#12542](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12542))
* rework DDIM, PLMS, UniPC to use CFG denoiser same as in k-diffusion samplers:
* makes all of them work with img2img
* makes prompt composition possible (AND)
* makes them available for SDXL
* always show extra networks tabs in the UI ([#11808](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11808))
* use less RAM when creating models ([#11958](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11958), [#12599](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12599))
* textual inversion inference support for SDXL
* extra networks UI: show metadata for SD checkpoints
* checkpoint merger: add metadata support
* prompt editing and attention: add support for whitespace after the number ([ red : green : 0.5 ]) (seed breaking change) ([#12177](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12177))
* VAE: allow selecting own VAE for each checkpoint (in user metadata editor)
* VAE: add selected VAE to infotext
* options in main UI: add own separate setting for txt2img and img2img, correctly read values from pasted infotext, add setting for column count ([#12551](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12551))
* add resize handle to txt2img and img2img tabs, allowing to change the amount of horizontable space given to generation parameters and resulting image gallery ([#12687](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12687), [#12723](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12723))
* change default behavior for batching cond/uncond -- now it's on by default, and is disabled by an UI setting (Optimizatios -> Batch cond/uncond) - if you are on lowvram/medvram and are getting OOM exceptions, you will need to enable it
* show current position in queue and make it so that requests are processed in the order of arrival ([#12707](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12707))
* add `--medvram-sdxl` flag that only enables `--medvram` for SDXL models
* prompt editing timeline has separate range for first pass and hires-fix pass (seed breaking change) ([#12457](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12457))
### Minor:
* img2img batch: RAM savings, VRAM savings, .tif, .tiff in img2img batch ([#12120](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12120), [#12514](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12514), [#12515](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12515))
* postprocessing/extras: RAM savings ([#12479](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12479))
* XYZ: in the axis labels, remove pathnames from model filenames
* XYZ: support hires sampler ([#12298](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12298))
* XYZ: new option: use text inputs instead of dropdowns ([#12491](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12491))
* add gradio version warning
* sort list of VAE checkpoints ([#12297](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12297))
* use transparent white for mask in inpainting, along with an option to select the color ([#12326](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12326))
* move some settings to their own section: img2img, VAE
* add checkbox to show/hide dirs for extra networks
* Add TAESD(or more) options for all the VAE encode/decode operation ([#12311](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12311))
* gradio theme cache, new gradio themes, along with explanation that the user can input his own values ([#12346](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12346), [#12355](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12355))
* sampler fixes/tweaks: s_tmax, s_churn, s_noise, s_tmax ([#12354](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12354), [#12356](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12356), [#12357](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12357), [#12358](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12358), [#12375](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12375), [#12521](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12521))
* update README.md with correct instructions for Linux installation ([#12352](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12352))
* option to not save incomplete images, on by default ([#12338](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12338))
* enable cond cache by default
* git autofix for repos that are corrupted ([#12230](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12230))
* allow to open images in new browser tab by middle mouse button ([#12379](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12379))
* automatically open webui in browser when running "locally" ([#12254](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12254))
* put commonly used samplers on top, make DPM++ 2M Karras the default choice
* zoom and pan: option to auto-expand a wide image, improved integration ([#12413](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12413), [#12727](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12727))
* option to cache Lora networks in memory
* rework hires fix UI to use accordion
* face restoration and tiling moved to settings - use "Options in main UI" setting if you want them back
* change quicksettings items to have variable width
* Lora: add Norm module, add support for bias ([#12503](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12503))
* Lora: output warnings in UI rather than fail for unfitting loras; switch to logging for error output in console
* support search and display of hashes for all extra network items ([#12510](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12510))
* add extra noise param for img2img operations ([#12564](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12564))
* support for Lora with bias ([#12584](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12584))
* make interrupt quicker ([#12634](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12634))
* configurable gallery height ([#12648](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12648))
* make results column sticky ([#12645](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12645))
* more hash filename patterns ([#12639](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12639))
* make image viewer actually fit the whole page ([#12635](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12635))
* make progress bar work independently from live preview display which results in it being updated a lot more often
* forbid Full live preview method for medvram and add a setting to undo the forbidding
* make it possible to localize tooltips and placeholders
* add option to align with sgm repo's sampling implementation ([#12818](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12818))
* Restore faces and Tiling generation parameters have been moved to settings out of main UI
* if you want to put them back into main UI, use `Options in main UI` setting on the UI page.
### Extensions and API:
* gradio 3.41.2
* also bump versions for packages: transformers, GitPython, accelerate, scikit-image, timm, tomesd
* support tooltip kwarg for gradio elements: gr.Textbox(label='hello', tooltip='world')
* properly clear the total console progressbar when using txt2img and img2img from API
* add cmd_arg --disable-extra-extensions and --disable-all-extensions ([#12294](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12294))
* shared.py and webui.py split into many files
* add --loglevel commandline argument for logging
* add a custom UI element that combines accordion and checkbox
* avoid importing gradio in tests because it spams warnings
* put infotext label for setting into OptionInfo definition rather than in a separate list
* make `StableDiffusionProcessingImg2Img.mask_blur` a property, make more inline with PIL `GaussianBlur` ([#12470](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12470))
* option to make scripts UI without gr.Group
* add a way for scripts to register a callback for before/after just a single component's creation
* use dataclass for StableDiffusionProcessing
* store patches for Lora in a specialized module instead of inside torch
* support http/https URLs in API ([#12663](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12663), [#12698](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12698))
* add extra noise callback ([#12616](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12616))
* dump current stack traces when exiting with SIGINT
* add type annotations for extra fields of shared.sd_model
### Bug Fixes:
* Don't crash if out of local storage quota for javascriot localStorage
* XYZ plot do not fail if an exception occurs
* fix missing TI hash in infotext if generation uses both negative and positive TI ([#12269](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12269))
* localization fixes ([#12307](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12307))
* fix sdxl model invalid configuration after the hijack
* correctly toggle extras checkbox for infotext paste ([#12304](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12304))
* open raw sysinfo link in new page ([#12318](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12318))
* prompt parser: Account for empty field in alternating words syntax ([#12319](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12319))
* add tab and carriage return to invalid filename chars ([#12327](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12327))
* fix api only Lora not working ([#12387](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12387))
* fix options in main UI misbehaving when there's just one element
* make it possible to use a sampler from infotext even if it's hidden in the dropdown
* fix styles missing from the prompt in infotext when making a grid of batch of multiplie images
* prevent bogus progress output in console when calculating hires fix dimensions
* fix --use-textbox-seed
* fix broken `Lora/Networks: use old method` option ([#12466](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12466))
* properly return `None` for VAE hash when using `--no-hashing` ([#12463](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12463))
* MPS/macOS fixes and optimizations ([#12526](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12526))
* add second_order to samplers that mistakenly didn't have it
* when refreshing cards in extra networks UI, do not discard user's custom resolution
* fix processing error that happens if batch_size is not a multiple of how many prompts/negative prompts there are ([#12509](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12509))
* fix inpaint upload for alpha masks ([#12588](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12588))
* fix exception when image sizes are not integers ([#12586](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12586))
* fix incorrect TAESD Latent scale ([#12596](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12596))
* auto add data-dir to gradio-allowed-path ([#12603](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12603))
* fix exception if extensuions dir is missing ([#12607](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12607))
* fix issues with api model-refresh and vae-refresh ([#12638](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12638))
* fix img2img background color for transparent images option not being used ([#12633](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12633))
* attempt to resolve NaN issue with unstable VAEs in fp32 mk2 ([#12630](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12630))
* implement missing undo hijack for SDXL
* fix xyz swap axes ([#12684](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12684))
* fix errors in backup/restore tab if any of config files are broken ([#12689](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12689))
* fix SD VAE switch error after model reuse ([#12685](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12685))
* fix trying to create images too large for the chosen format ([#12667](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12667))
* create Gradio temp directory if necessary ([#12717](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12717))
* prevent possible cache loss if exiting as it's being written by using an atomic operation to replace the cache with the new version
* set devices.dtype_unet correctly
* run RealESRGAN on GPU for non-CUDA devices ([#12737](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
* prevent extra network buttons being obscured by description for very small card sizes ([#12745](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12745))
* fix error that causes some extra networks to be disabled if both <lora:> and <lyco:> are present in the prompt
* fix defaults settings page breaking when any of main UI tabs are hidden
* fix incorrect save/display of new values in Defaults page in settings
* fix for Reload UI function: if you reload UI on one tab, other opened tabs will no longer stop working
* fix an error that prevents VAE being reloaded after an option change if a VAE near the checkpoint exists ([#12797](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
* hide broken image crop tool ([#12792](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
* don't show hidden samplers in dropdown for XYZ script ([#12780](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
* fix style editing dialog breaking if it's opened in both img2img and txt2img tabs
* fix a bug allowing users to bypass gradio and API authentication (reported by vysecurity)
* fix notification not playing when built-in webui tab is inactive ([#12834](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12834))
* honor `--skip-install` for extension installers ([#12832](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12832))
* don't print blank stdout in extension installers ([#12833](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12832), [#12855](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12855))
* do not change quicksettings dropdown option when value returned is `None` ([#12854](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12854))
* get progressbar to display correctly in extensions tab
## 1.5.2
### Bug Fixes:
* fix memory leak when generation fails
* update doggettx cross attention optimization to not use an unreasonable amount of memory in some edge cases -- suggestion by MorkTheOrk
## 1.5.1
### Minor:
* support parsing text encoder blocks in some new LoRAs
* delete scale checker script due to user demand
### Extensions and API:
* add postprocess_batch_list script callback
### Bug Fixes:
* fix TI training for SD1
* fix reload altclip model error
* prepend the pythonpath instead of overriding it
* fix typo in SD_WEBUI_RESTARTING
* if txt2img/img2img raises an exception, finally call state.end()
* fix composable diffusion weight parsing
* restyle Startup profile for black users
* fix webui not launching with --nowebui
* catch exception for non git extensions
* fix some options missing from /sdapi/v1/options
* fix for extension update status always saying "unknown"
* fix display of extra network cards that have `<>` in the name
* update lora extension to work with python 3.8
## 1.5.0
### Features:
* SD XL support
* user metadata system for custom networks
* extended Lora metadata editor: set activation text, default weight, view tags, training info
* Lora extension rework to include other types of networks (all that were previously handled by LyCORIS extension)
* show github stars for extensions
* img2img batch mode can read extra stuff from png info
* img2img batch works with subdirectories
* hotkeys to move prompt elements: alt+left/right
* restyle time taken/VRAM display
* add textual inversion hashes to infotext
* optimization: cache git extension repo information
* move generate button next to the generated picture for mobile clients
* hide cards for networks of incompatible Stable Diffusion version in Lora extra networks interface
* skip installing packages with pip if they all are already installed - startup speedup of about 2 seconds
### Minor:
* checkbox to check/uncheck all extensions in the Installed tab
* add gradio user to infotext and to filename patterns
* allow gif for extra network previews
* add options to change colors in grid
* use natural sort for items in extra networks
* Mac: use empty_cache() from torch 2 to clear VRAM
* added automatic support for installing the right libraries for Navi3 (AMD)
* add option SWIN_torch_compile to accelerate SwinIR upscale
* suppress printing TI embedding info at start to console by default
* speedup extra networks listing
* added `[none]` filename token.
* removed thumbs extra networks view mode (use settings tab to change width/height/scale to get thumbs)
* add always_discard_next_to_last_sigma option to XYZ plot
* automatically switch to 32-bit float VAE if the generated picture has NaNs without the need for `--no-half-vae` commandline flag.
### Extensions and API:
* api endpoints: /sdapi/v1/server-kill, /sdapi/v1/server-restart, /sdapi/v1/server-stop
* allow Script to have custom metaclass
* add model exists status check /sdapi/v1/options
* rename --add-stop-route to --api-server-stop
* add `before_hr` script callback
* add callback `after_extra_networks_activate`
* disable rich exception output in console for API by default, use WEBUI_RICH_EXCEPTIONS env var to enable
* return http 404 when thumb file not found
* allow replacing extensions index with environment variable
### Bug Fixes:
* fix for catch errors when retrieving extension index #11290
* fix very slow loading speed of .safetensors files when reading from network drives
* API cache cleanup
* fix UnicodeEncodeError when writing to file CLIP Interrogator batch mode
* fix warning of 'has_mps' deprecated from PyTorch
* fix problem with extra network saving images as previews losing generation info
* fix throwing exception when trying to resize image with I;16 mode
* fix for #11534: canvas zoom and pan extension hijacking shortcut keys
* fixed launch script to be runnable from any directory
* don't add "Seed Resize: -1x-1" to API image metadata
* correctly remove end parenthesis with ctrl+up/down
* fixing --subpath on newer gradio version
* fix: check fill size none zero when resize (fixes #11425)
* use submit and blur for quick settings textbox
* save img2img batch with images.save_image()
* prevent running preload.py for disabled extensions
* fix: previously, model name was added together with directory name to infotext and to [model_name] filename pattern; directory name is now not included
## 1.4.1
### Bug Fixes:
* add queue lock for refresh-checkpoints
## 1.4.0
### Features:
* zoom controls for inpainting
* run basic torch calculation at startup in parallel to reduce the performance impact of first generation
* option to pad prompt/neg prompt to be same length
* remove taming_transformers dependency
* custom k-diffusion scheduler settings
* add an option to show selected settings in main txt2img/img2img UI
* sysinfo tab in settings
* infer styles from prompts when pasting params into the UI
* an option to control the behavior of the above
### Minor:
* bump Gradio to 3.32.0
* bump xformers to 0.0.20
* Add option to disable token counters
* tooltip fixes & optimizations
* make it possible to configure filename for the zip download
* `[vae_filename]` pattern for filenames
* Revert discarding penultimate sigma for DPM-Solver++(2M) SDE
* change UI reorder setting to multiselect
* read version info form CHANGELOG.md if git version info is not available
* link footer API to Wiki when API is not active
* persistent conds cache (opt-in optimization)
### Extensions:
* After installing extensions, webui properly restarts the process rather than reloads the UI
* Added VAE listing to web API. Via: /sdapi/v1/sd-vae
* custom unet support
* Add onAfterUiUpdate callback
* refactor EmbeddingDatabase.register_embedding() to allow unregistering
* add before_process callback for scripts
* add ability for alwayson scripts to specify section and let user reorder those sections
### Bug Fixes:
* Fix dragging text to prompt
* fix incorrect quoting for infotext values with colon in them
* fix "hires. fix" prompt sharing same labels with txt2img_prompt
* Fix s_min_uncond default type int
* Fix for #10643 (Inpainting mask sometimes not working)
* fix bad styling for thumbs view in extra networks #10639
* fix for empty list of optimizations #10605
* small fixes to prepare_tcmalloc for Debian/Ubuntu compatibility
* fix --ui-debug-mode exit
* patch GitPython to not use leaky persistent processes
* fix duplicate Cross attention optimization after UI reload
* torch.cuda.is_available() check for SdOptimizationXformers
* fix hires fix using wrong conds in second pass if using Loras.
* handle exception when parsing generation parameters from png info
* fix upcast attention dtype error
* forcing Torch Version to 1.13.1 for RX 5000 series GPUs
* split mask blur into X and Y components, patch Outpainting MK2 accordingly
* don't die when a LoRA is a broken symlink
* allow activation of Generate Forever during generation
## 1.3.2
### Bug Fixes:
* fix files served out of tmp directory even if they are saved to disk
* fix postprocessing overwriting parameters
## 1.3.1
### Features:
* revert default cross attention optimization to Doggettx
### Bug Fixes:
* fix bug: LoRA don't apply on dropdown list sd_lora
* fix png info always added even if setting is not enabled
* fix some fields not applying in xyz plot
* fix "hires. fix" prompt sharing same labels with txt2img_prompt
* fix lora hashes not being added properly to infotex if there is only one lora
* fix --use-cpu failing to work properly at startup
* make --disable-opt-split-attention command line option work again
## 1.3.0
### Features:
* add UI to edit defaults
* token merging (via dbolya/tomesd)
* settings tab rework: add a lot of additional explanations and links
* load extensions' Git metadata in parallel to loading the main program to save a ton of time during startup
* update extensions table: show branch, show date in separate column, and show version from tags if available
* TAESD - another option for cheap live previews
* allow choosing sampler and prompts for second pass of hires fix - hidden by default, enabled in settings
* calculate hashes for Lora
* add lora hashes to infotext
* when pasting infotext, use infotext's lora hashes to find local loras for `<lora:xxx:1>` entries whose hashes match loras the user has
* select cross attention optimization from UI
### Minor:
* bump Gradio to 3.31.0
* bump PyTorch to 2.0.1 for macOS and Linux AMD
* allow setting defaults for elements in extensions' tabs
* allow selecting file type for live previews
* show "Loading..." for extra networks when displaying for the first time
* suppress ENSD infotext for samplers that don't use it
* clientside optimizations
* add options to show/hide hidden files and dirs in extra networks, and to not list models/files in hidden directories
* allow whitespace in styles.csv
* add option to reorder tabs
* move some functionality (swap resolution and set seed to -1) to client
* option to specify editor height for img2img
* button to copy image resolution into img2img width/height sliders
* switch from pyngrok to ngrok-py
* lazy-load images in extra networks UI
* set "Navigate image viewer with gamepad" option to false by default, by request
* change upscalers to download models into user-specified directory (from commandline args) rather than the default models/<...>
* allow hiding buttons in ui-config.json
### Extensions:
* add /sdapi/v1/script-info api
* use Ruff to lint Python code
* use ESlint to lint Javascript code
* add/modify CFG callbacks for Self-Attention Guidance extension
* add command and endpoint for graceful server stopping
* add some locals (prompts/seeds/etc) from processing function into the Processing class as fields
* rework quoting for infotext items that have commas in them to use JSON (should be backwards compatible except for cases where it didn't work previously)
* add /sdapi/v1/refresh-loras api checkpoint post request
* tests overhaul
### Bug Fixes:
* fix an issue preventing the program from starting if the user specifies a bad Gradio theme
* fix broken prompts from file script
* fix symlink scanning for extra networks
* fix --data-dir ignored when launching via webui-user.bat COMMANDLINE_ARGS
* allow web UI to be ran fully offline
* fix inability to run with --freeze-settings
* fix inability to merge checkpoint without adding metadata
* fix extra networks' save preview image not adding infotext for jpeg/webm
* remove blinking effect from text in hires fix and scale resolution preview
* make links to `http://<...>.git` extensions work in the extension tab
* fix bug with webui hanging at startup due to hanging git process
## 1.2.1
### Features:
* add an option to always refer to LoRA by filenames
### Bug Fixes:
* never refer to LoRA by an alias if multiple LoRAs have same alias or the alias is called none
* fix upscalers disappearing after the user reloads UI
* allow bf16 in safe unpickler (resolves problems with loading some LoRAs)
* allow web UI to be ran fully offline
* fix localizations not working
* fix error for LoRAs: `'LatentDiffusion' object has no attribute 'lora_layer_mapping'`
## 1.2.0
### Features:
* do not wait for Stable Diffusion model to load at startup
* add filename patterns: `[denoising]`
* directory hiding for extra networks: dirs starting with `.` will hide their cards on extra network tabs unless specifically searched for
* LoRA: for the `<...>` text in prompt, use name of LoRA that is in the metadata of the file, if present, instead of filename (both can be used to activate LoRA)
* LoRA: read infotext params from kohya-ss's extension parameters if they are present and if his extension is not active
* LoRA: fix some LoRAs not working (ones that have 3x3 convolution layer)
* LoRA: add an option to use old method of applying LoRAs (producing same results as with kohya-ss)
* add version to infotext, footer and console output when starting
* add links to wiki for filename pattern settings
* add extended info for quicksettings setting and use multiselect input instead of a text field
### Minor:
* bump Gradio to 3.29.0
* bump PyTorch to 2.0.1
* `--subpath` option for gradio for use with reverse proxy
* Linux/macOS: use existing virtualenv if already active (the VIRTUAL_ENV environment variable)
* do not apply localizations if there are none (possible frontend optimization)
* add extra `None` option for VAE in XYZ plot
* print error to console when batch processing in img2img fails
* create HTML for extra network pages only on demand
* allow directories starting with `.` to still list their models for LoRA, checkpoints, etc
* put infotext options into their own category in settings tab
* do not show licenses page when user selects Show all pages in settings
### Extensions:
* tooltip localization support
* add API method to get LoRA models with prompt
### Bug Fixes:
* re-add `/docs` endpoint
* fix gamepad navigation
* make the lightbox fullscreen image function properly
* fix squished thumbnails in extras tab
* keep "search" filter for extra networks when user refreshes the tab (previously it showed everything after you refreshed)
* fix webui showing the same image if you configure the generation to always save results into same file
* fix bug with upscalers not working properly
* fix MPS on PyTorch 2.0.1, Intel Macs
* make it so that custom context menu from contextMenu.js only disappears after user's click, ignoring non-user click events
* prevent Reload UI button/link from reloading the page when it's not yet ready
* fix prompts from file script failing to read contents from a drag/drop file
## 1.1.1
### Bug Fixes:
* fix an error that prevents running webui on PyTorch<2.0 without --disable-safe-unpickle
## 1.1.0
### Features:
* switch to PyTorch 2.0.0 (except for AMD GPUs)
* visual improvements to custom code scripts
* add filename patterns: `[clip_skip]`, `[hasprompt<>]`, `[batch_number]`, `[generation_number]`
* add support for saving init images in img2img, and record their hashes in infotext for reproducibility
* automatically select current word when adjusting weight with ctrl+up/down
* add dropdowns for X/Y/Z plot
* add setting: Stable Diffusion/Random number generator source: makes it possible to make images generated from a given manual seed consistent across different GPUs
* support Gradio's theme API
* use TCMalloc on Linux by default; possible fix for memory leaks
* add optimization option to remove negative conditioning at low sigma values #9177
* embed model merge metadata in .safetensors file
* extension settings backup/restore feature #9169
* add "resize by" and "resize to" tabs to img2img
* add option "keep original size" to textual inversion images preprocess
* image viewer scrolling via analog stick
* button to restore the progress from session lost / tab reload
### Minor:
* bump Gradio to 3.28.1
* change "scale to" to sliders in Extras tab
* add labels to tool buttons to make it possible to hide them
* add tiled inference support for ScuNET
* add branch support for extension installation
* change Linux installation script to install into current directory rather than `/home/username`
* sort textual inversion embeddings by name (case-insensitive)
* allow styles.csv to be symlinked or mounted in docker
* remove the "do not add watermark to images" option
* make selected tab configurable with UI config
* make the extra networks UI fixed height and scrollable
* add `disable_tls_verify` arg for use with self-signed certs
### Extensions:
* add reload callback
* add `is_hr_pass` field for processing
### Bug Fixes:
* fix broken batch image processing on 'Extras/Batch Process' tab
* add "None" option to extra networks dropdowns
* fix FileExistsError for CLIP Interrogator
* fix /sdapi/v1/txt2img endpoint not working on Linux #9319
* fix disappearing live previews and progressbar during slow tasks
* fix fullscreen image view not working properly in some cases
* prevent alwayson_scripts args param resizing script_arg list when they are inserted in it
* fix prompt schedule for second order samplers
* fix image mask/composite for weird resolutions #9628
* use correct images for previews when using AND (see #9491)
* one broken image in img2img batch won't stop all processing
* fix image orientation bug in train/preprocess
* fix Ngrok recreating tunnels every reload
* fix `--realesrgan-models-path` and `--ldsr-models-path` not working
* fix `--skip-install` not working
* use SAMPLE file format in Outpainting Mk2 & Poorman
* do not fail all LoRAs if some have failed to load when making a picture
## 1.0.0
* everything
================================================
FILE: CITATION.cff
================================================
cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- given-names: AUTOMATIC1111
title: "Stable Diffusion Web UI"
date-released: 2022-08-22
url: "https://github.com/AUTOMATIC1111/stable-diffusion-webui"
================================================
FILE: CODEOWNERS
================================================
* @lllyasviel
================================================
FILE: LICENSE.txt
================================================
GNU AFFERO GENERAL PUBLIC LICENSE
Version 3, 19 November 2007
Copyright (c) 2023 AUTOMATIC1111
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU Affero General Public License is a free, copyleft license for
software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
Developers that use our General Public Licenses protect your rights
with two steps: (1) assert copyright on the software, and (2) offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
A secondary benefit of defending all users' freedom is that
improvements made in alternate versions of the program, if they
receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
encouraged by the resulting cooperation. However, in the case of
software used on network servers, this result may fail to come about.
The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
The GNU Affero General Public License is designed specifically to
ensure that, in such cases, the modified source code becomes available
to the community. It requires the operator of a network server to
provide the source code of the modified version running there to the
users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
An older license, called the Affero General Public License and
published by Affero, was designed to accomplish similar goals. This is
a different license, not a version of the Affero GPL, but Affero has
released a new version of the Affero GPL which permits relicensing under
this license.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU Affero General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Remote Network Interaction; Use with the GNU General Public License.
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
Source of your version by providing access to the Corresponding Source
from a network server at no charge, through some standard or customary
means of facilitating copying of software. This Corresponding Source
shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU Affero General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If your software can interact with users remotely through a computer
network, you should also make sure that it provides a way for users to
get its source. For example, if your program is a web application, its
interface could display a "Source" link that leads users to an archive
of the code. There are many ways you could offer source, and different
solutions will be better for different programs; see section 13 for the
specific requirements.
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
<https://www.gnu.org/licenses/>.
---------------------------------Facebook BNB-------------------------------
MIT License
Copyright (c) Facebook, Inc. and its affiliates.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
================================================
FILE: NEWS.md
================================================
About Gradio 5: will try to upgrade to Gradio 5 at about 2025 March. If failed, then will try again on about 2025 June. relatively positive that we can have Gradio5 before next summer.
2024 Oct 28: A new branch `sd35` is contributed by [#2183](https://github.com/lllyasviel/stable-diffusion-webui-forge/pull/2183) . I will take a look at quants and sampling and transformer's clip-g vs that clip-g rewrite before merging to main ... (Oct 29: okay maybe medium also need to take a look later)
About Flux ControlNet (sync [here](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/932)): The rewrite of ControlNet Intergrated will ~start at about Sep 29~ (delayed) ~start at about Oct 15~ (delayed) ~start at about Oct 30~ (delayed) start at about Nov 20. (When this note is announced, the main targets include some diffusers formatted Flux ControlNets and some community implementation of Union ControlNets. However, this may be extended if stronger models come out after this note.)
2024 Sep 7: New sampler `Flux Realistic` is available now! Recommended scheduler is "simple".
================================================
FILE: README.md
================================================
# Stable Diffusion WebUI Forge
Stable Diffusion WebUI Forge is a platform on top of [Stable Diffusion WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui) (based on [Gradio](https://www.gradio.app/) <a href='https://github.com/gradio-app/gradio'><img src='https://img.shields.io/github/stars/gradio-app/gradio'></a>) to make development easier, optimize resource management, speed up inference, and study experimental features.
The name "Forge" is inspired from "Minecraft Forge". This project is aimed at becoming SD WebUI's Forge.
Forge is currently based on SD-WebUI 1.10.1 at [this commit](https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/82a973c04367123ae98bd9abdf80d9eda9b910e2). (Because original SD-WebUI is almost static now, Forge will sync with original WebUI every 90 days, or when important fixes.)
News are moved to this link: [Click here to see the News section](https://github.com/lllyasviel/stable-diffusion-webui-forge/blob/main/NEWS.md)
# Quick List
[Gradio 4 UI Must Read (TLDR: You need to use RIGHT MOUSE BUTTON to move canvas!)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/853)
[Flux Tutorial (BitsandBytes Models, NF4, "GPU Weight", "Offload Location", "Offload Method", etc)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/981)
[Flux Tutorial 2 (Seperated Full Models, GGUF, Technically Correct Comparison between GGUF and NF4, etc)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1050)
[Forge Extension List and Extension Replacement List (Temporary)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1754)
[How to make LoRAs more precise on low-bit models; How to Skip" Patching LoRAs"; How to only load LoRA one time rather than each generation; How to report LoRAs that do not work](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1038)
[Report Flux Performance Problems (TLDR: DO NOT set "GPU Weight" too high! Lower "GPU Weight" solves 99% problems!)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1181)
[How to solve "Connection errored out" / "Press anykey to continue ..." / etc](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1474)
[(Save Flux BitsandBytes UNet/Checkpoint)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1224#discussioncomment-10384104)
[LayerDiffuse Transparent Image Editing](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/854)
[Tell us what is missing in ControlNet Integrated](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/932)
[(Policy) Soft Advertisement Removal Policy](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1286)
(Flux BNB NF4 / GGUF Q8_0/Q5_0/Q5_1/Q4_0/Q4_1 are all natively supported with GPU weight slider and Quene/Async Swap toggle and swap location toggle. All Flux BNB NF4 / GGUF Q8_0/Q5_0/Q4_0 have LoRA support.)
# Installing Forge
**Just use this one-click installation package (with git and python included).**
[>>> Click Here to Download One-Click Package (CUDA 12.1 + Pytorch 2.3.1) <<<](https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/download/latest/webui_forge_cu121_torch231.7z)
Some other CUDA/Torch Versions:
[Forge with CUDA 12.1 + Pytorch 2.3.1](https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/download/latest/webui_forge_cu121_torch231.7z) <- **Recommended**
[Forge with CUDA 12.4 + Pytorch 2.4](https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/download/latest/webui_forge_cu124_torch24.7z) <- **Fastest**, but MSVC may be broken, xformers may not work
[Forge with CUDA 12.1 + Pytorch 2.1](https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/download/latest/webui_forge_cu121_torch21.7z) <- the previously used old environments
After you download, you uncompress, use `update.bat` to update, and use `run.bat` to run.
Note that running `update.bat` is important, otherwise you may be using a previous version with potential bugs unfixed.
### Advanced Install
If you are proficient in Git and you want to install Forge as another branch of SD-WebUI, please see [here](https://github.com/continue-revolution/sd-webui-animatediff/blob/forge/master/docs/how-to-use.md#you-have-a1111-and-you-know-git). In this way, you can reuse all SD checkpoints and all extensions you installed previously in your OG SD-WebUI, but you should know what you are doing.
If you know what you are doing, you can also install Forge using same method as SD-WebUI. (Install Git, Python, Git Clone the forge repo `https://github.com/lllyasviel/stable-diffusion-webui-forge.git` and then run webui-user.bat).
### Previous Versions
You can download previous versions [here](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/849).
# Forge Status
Based on manual test one-by-one:
| Component | Status | Last Test |
|-----------------------------------------------------|---------------------------------------------|--------------|
| Basic Diffusion | Normal | 2024 Aug 26 |
| GPU Memory Management System | Normal | 2024 Aug 26 |
| LoRAs | Normal | 2024 Aug 26 |
| All Preprocessors | Normal | 2024 Aug 26 |
| All ControlNets | Normal | 2024 Aug 26 |
| All IP-Adapters | Normal | 2024 Aug 26 |
| All Instant-IDs | Normal | 2024 July 27 |
| All Reference-only Methods | Normal | 2024 July 27 |
| All Integrated Extensions | Normal | 2024 July 27 |
| Popular Extensions (Adetailer, etc) | Normal | 2024 July 27 |
| Gradio 4 UIs | Normal | 2024 July 27 |
| Gradio 4 Forge Canvas | Normal | 2024 Aug 26 |
| LoRA/Checkpoint Selection UI for Gradio 4 | Normal | 2024 July 27 |
| Photopea/OpenposeEditor/etc for ControlNet | Normal | 2024 July 27 |
| Wacom 128 level touch pressure support for Canvas | Normal | 2024 July 15 |
| Microsoft Surface touch pressure support for Canvas | Broken, pending fix | 2024 July 29 |
| ControlNets (Union) | Not implemented yet, pending implementation | 2024 Aug 26 |
| ControlNets (Flux) | Not implemented yet, pending implementation | 2024 Aug 26 |
| API endpoints (txt2img, img2img, etc) | Normal, but pending improved Flux support | 2024 Aug 29 |
| OFT LoRAs | Broken, pending fix | 2024 Sep 9 |
Feel free to open issue if anything is broken and I will take a look every several days. If I do not update this "Forge Status" then it means I cannot reproduce any problem. In that case, fresh re-install should help most.
# UnetPatcher
Below are self-supported **single file** of all codes to implement FreeU V2.
See also `extension-builtin/sd_forge_freeu/scripts/forge_freeu.py`:
```python
import torch
import gradio as gr
from modules import scripts
def Fourier_filter(x, threshold, scale):
# FFT
x_freq = torch.fft.fftn(x.float(), dim=(-2, -1))
x_freq = torch.fft.fftshift(x_freq, dim=(-2, -1))
B, C, H, W = x_freq.shape
mask = torch.ones((B, C, H, W), device=x.device)
crow, ccol = H // 2, W // 2
mask[..., crow - threshold:crow + threshold, ccol - threshold:ccol + threshold] = scale
x_freq = x_freq * mask
# IFFT
x_freq = torch.fft.ifftshift(x_freq, dim=(-2, -1))
x_filtered = torch.fft.ifftn(x_freq, dim=(-2, -1)).real
return x_filtered.to(x.dtype)
def patch_freeu_v2(unet_patcher, b1, b2, s1, s2):
model_channels = unet_patcher.model.diffusion_model.config["model_channels"]
scale_dict = {model_channels * 4: (b1, s1), model_channels * 2: (b2, s2)}
on_cpu_devices = {}
def output_block_patch(h, hsp, transformer_options):
scale = scale_dict.get(h.shape[1], None)
if scale is not None:
hidden_mean = h.mean(1).unsqueeze(1)
B = hidden_mean.shape[0]
hidden_max, _ = torch.max(hidden_mean.view(B, -1), dim=-1, keepdim=True)
hidden_min, _ = torch.min(hidden_mean.view(B, -1), dim=-1, keepdim=True)
hidden_mean = (hidden_mean - hidden_min.unsqueeze(2).unsqueeze(3)) / (hidden_max - hidden_min).unsqueeze(2).unsqueeze(3)
h[:, :h.shape[1] // 2] = h[:, :h.shape[1] // 2] * ((scale[0] - 1) * hidden_mean + 1)
if hsp.device not in on_cpu_devices:
try:
hsp = Fourier_filter(hsp, threshold=1, scale=scale[1])
except:
print("Device", hsp.device, "does not support the torch.fft.")
on_cpu_devices[hsp.device] = True
hsp = Fourier_filter(hsp.cpu(), threshold=1, scale=scale[1]).to(hsp.device)
else:
hsp = Fourier_filter(hsp.cpu(), threshold=1, scale=scale[1]).to(hsp.device)
return h, hsp
m = unet_patcher.clone()
m.set_model_output_block_patch(output_block_patch)
return m
class FreeUForForge(scripts.Script):
sorting_priority = 12 # It will be the 12th item on UI.
def title(self):
return "FreeU Integrated"
def show(self, is_img2img):
# make this extension visible in both txt2img and img2img tab.
return scripts.AlwaysVisible
def ui(self, *args, **kwargs):
with gr.Accordion(open=False, label=self.title()):
freeu_enabled = gr.Checkbox(label='Enabled', value=False)
freeu_b1 = gr.Slider(label='B1', minimum=0, maximum=2, step=0.01, value=1.01)
freeu_b2 = gr.Slider(label='B2', minimum=0, maximum=2, step=0.01, value=1.02)
freeu_s1 = gr.Slider(label='S1', minimum=0, maximum=4, step=0.01, value=0.99)
freeu_s2 = gr.Slider(label='S2', minimum=0, maximum=4, step=0.01, value=0.95)
return freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2
def process_before_every_sampling(self, p, *script_args, **kwargs):
# This will be called before every sampling.
# If you use highres fix, this will be called twice.
freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2 = script_args
if not freeu_enabled:
return
unet = p.sd_model.forge_objects.unet
unet = patch_freeu_v2(unet, freeu_b1, freeu_b2, freeu_s1, freeu_s2)
p.sd_model.forge_objects.unet = unet
# Below codes will add some logs to the texts below the image outputs on UI.
# The extra_generation_params does not influence results.
p.extra_generation_params.update(dict(
freeu_enabled=freeu_enabled,
freeu_b1=freeu_b1,
freeu_b2=freeu_b2,
freeu_s1=freeu_s1,
freeu_s2=freeu_s2,
))
return
```
See also [Forge's Unet Implementation](https://github.com/lllyasviel/stable-diffusion-webui-forge/blob/main/backend/nn/unet.py).
# Under Construction
WebUI Forge is now under some constructions, and docs / UI / functionality may change with updates.
================================================
FILE: _typos.toml
================================================
[default.extend-words]
# Part of "RGBa" (Pillow's pre-multiplied alpha RGB mode)
Ba = "Ba"
# HSA is something AMD uses for their GPUs
HSA = "HSA"
================================================
FILE: backend/README.md
================================================
# WIP Backend for Forge
================================================
FILE: backend/args.py
================================================
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("--gpu-device-id", type=int, default=None, metavar="DEVICE_ID")
fp_group = parser.add_mutually_exclusive_group()
fp_group.add_argument("--all-in-fp32", action="store_true")
fp_group.add_argument("--all-in-fp16", action="store_true")
fpunet_group = parser.add_mutually_exclusive_group()
fpunet_group.add_argument("--unet-in-bf16", action="store_true")
fpunet_group.add_argument("--unet-in-fp16", action="store_true")
fpunet_group.add_argument("--unet-in-fp8-e4m3fn", action="store_true")
fpunet_group.add_argument("--unet-in-fp8-e5m2", action="store_true")
fpvae_group = parser.add_mutually_exclusive_group()
fpvae_group.add_argument("--vae-in-fp16", action="store_true")
fpvae_group.add_argument("--vae-in-fp32", action="store_true")
fpvae_group.add_argument("--vae-in-bf16", action="store_true")
parser.add_argument("--vae-in-cpu", action="store_true")
fpte_group = parser.add_mutually_exclusive_group()
fpte_group.add_argument("--clip-in-fp8-e4m3fn", action="store_true")
fpte_group.add_argument("--clip-in-fp8-e5m2", action="store_true")
fpte_group.add_argument("--clip-in-fp16", action="store_true")
fpte_group.add_argument("--clip-in-fp32", action="store_true")
attn_group = parser.add_mutually_exclusive_group()
attn_group.add_argument("--attention-split", action="store_true")
attn_group.add_argument("--attention-quad", action="store_true")
attn_group.add_argument("--attention-pytorch", action="store_true")
upcast = parser.add_mutually_exclusive_group()
upcast.add_argument("--force-upcast-attention", action="store_true")
upcast.add_argument("--disable-attention-upcast", action="store_true")
parser.add_argument("--disable-xformers", action="store_true")
parser.add_argument("--directml", type=int, nargs="?", metavar="DIRECTML_DEVICE", const=-1)
parser.add_argument("--disable-ipex-hijack", action="store_true")
vram_group = parser.add_mutually_exclusive_group()
vram_group.add_argument("--always-gpu", action="store_true")
vram_group.add_argument("--always-high-vram", action="store_true")
vram_group.add_argument("--always-normal-vram", action="store_true")
vram_group.add_argument("--always-low-vram", action="store_true")
vram_group.add_argument("--always-no-vram", action="store_true")
vram_group.add_argument("--always-cpu", action="store_true")
parser.add_argument("--always-offload-from-vram", action="store_true")
parser.add_argument("--pytorch-deterministic", action="store_true")
parser.add_argument("--cuda-malloc", action="store_true")
parser.add_argument("--cuda-stream", action="store_true")
parser.add_argument("--pin-shared-memory", action="store_true")
parser.add_argument("--disable-gpu-warning", action="store_true")
args = parser.parse_known_args()[0]
# Some dynamic args that may be changed by webui rather than cmd flags.
dynamic_args = dict(
embedding_dir='./embeddings',
emphasis_name='original'
)
================================================
FILE: backend/attention.py
================================================
import math
import torch
import einops
from backend.args import args
from backend import memory_management
from backend.misc.sub_quadratic_attention import efficient_dot_product_attention
BROKEN_XFORMERS = False
if memory_management.xformers_enabled():
import xformers
import xformers.ops
try:
x_vers = xformers.__version__
BROKEN_XFORMERS = x_vers.startswith("0.0.2") and not x_vers.startswith("0.0.20")
except:
pass
FORCE_UPCAST_ATTENTION_DTYPE = memory_management.force_upcast_attention_dtype()
def get_attn_precision(attn_precision=torch.float32):
if args.disable_attention_upcast:
return None
if FORCE_UPCAST_ATTENTION_DTYPE is not None:
return FORCE_UPCAST_ATTENTION_DTYPE
return attn_precision
def exists(val):
return val is not None
def attention_basic(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False):
attn_precision = get_attn_precision(attn_precision)
if skip_reshape:
b, _, _, dim_head = q.shape
else:
b, _, dim_head = q.shape
dim_head //= heads
scale = dim_head ** -0.5
h = heads
if skip_reshape:
q, k, v = map(
lambda t: t.reshape(b * heads, -1, dim_head),
(q, k, v),
)
else:
q, k, v = map(
lambda t: t.unsqueeze(3)
.reshape(b, -1, heads, dim_head)
.permute(0, 2, 1, 3)
.reshape(b * heads, -1, dim_head)
.contiguous(),
(q, k, v),
)
if attn_precision == torch.float32:
sim = torch.einsum('b i d, b j d -> b i j', q.float(), k.float()) * scale
else:
sim = torch.einsum('b i d, b j d -> b i j', q, k) * scale
del q, k
if exists(mask):
if mask.dtype == torch.bool:
mask = einops.rearrange(mask, 'b ... -> b (...)')
max_neg_value = -torch.finfo(sim.dtype).max
mask = einops.repeat(mask, 'b j -> (b h) () j', h=h)
sim.masked_fill_(~mask, max_neg_value)
else:
if len(mask.shape) == 2:
bs = 1
else:
bs = mask.shape[0]
mask = mask.reshape(bs, -1, mask.shape[-2], mask.shape[-1]).expand(b, heads, -1, -1).reshape(-1, mask.shape[-2], mask.shape[-1])
sim.add_(mask)
sim = sim.softmax(dim=-1)
out = torch.einsum('b i j, b j d -> b i d', sim.to(v.dtype), v)
out = (
out.unsqueeze(0)
.reshape(b, heads, -1, dim_head)
.permute(0, 2, 1, 3)
.reshape(b, -1, heads * dim_head)
)
return out
def attention_sub_quad(query, key, value, heads, mask=None, attn_precision=None, skip_reshape=False):
attn_precision = get_attn_precision(attn_precision)
if skip_reshape:
b, _, _, dim_head = query.shape
else:
b, _, dim_head = query.shape
dim_head //= heads
scale = dim_head ** -0.5
if skip_reshape:
query = query.reshape(b * heads, -1, dim_head)
value = value.reshape(b * heads, -1, dim_head)
key = key.reshape(b * heads, -1, dim_head).movedim(1, 2)
else:
query = query.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head)
value = value.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head)
key = key.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 3, 1).reshape(b * heads, dim_head, -1)
dtype = query.dtype
upcast_attention = attn_precision == torch.float32 and query.dtype != torch.float32
if upcast_attention:
bytes_per_token = torch.finfo(torch.float32).bits // 8
else:
bytes_per_token = torch.finfo(query.dtype).bits // 8
batch_x_heads, q_tokens, _ = query.shape
_, _, k_tokens = key.shape
qk_matmul_size_bytes = batch_x_heads * bytes_per_token * q_tokens * k_tokens
mem_free_total, mem_free_torch = memory_management.get_free_memory(query.device, True)
kv_chunk_size_min = None
kv_chunk_size = None
query_chunk_size = None
for x in [4096, 2048, 1024, 512, 256]:
count = mem_free_total / (batch_x_heads * bytes_per_token * x * 4.0)
if count >= k_tokens:
kv_chunk_size = k_tokens
query_chunk_size = x
break
if query_chunk_size is None:
query_chunk_size = 512
if mask is not None:
if len(mask.shape) == 2:
bs = 1
else:
bs = mask.shape[0]
mask = mask.reshape(bs, -1, mask.shape[-2], mask.shape[-1]).expand(b, heads, -1, -1).reshape(-1, mask.shape[-2], mask.shape[-1])
hidden_states = efficient_dot_product_attention(
query,
key,
value,
query_chunk_size=query_chunk_size,
kv_chunk_size=kv_chunk_size,
kv_chunk_size_min=kv_chunk_size_min,
use_checkpoint=False,
upcast_attention=upcast_attention,
mask=mask,
)
hidden_states = hidden_states.to(dtype)
hidden_states = hidden_states.unflatten(0, (-1, heads)).transpose(1, 2).flatten(start_dim=2)
return hidden_states
def attention_split(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False):
attn_precision = get_attn_precision(attn_precision)
if skip_reshape:
b, _, _, dim_head = q.shape
else:
b, _, dim_head = q.shape
dim_head //= heads
scale = dim_head ** -0.5
h = heads
if skip_reshape:
q, k, v = map(
lambda t: t.reshape(b * heads, -1, dim_head),
(q, k, v),
)
else:
q, k, v = map(
lambda t: t.unsqueeze(3)
.reshape(b, -1, heads, dim_head)
.permute(0, 2, 1, 3)
.reshape(b * heads, -1, dim_head)
.contiguous(),
(q, k, v),
)
r1 = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype)
mem_free_total = memory_management.get_free_memory(q.device)
if attn_precision == torch.float32:
element_size = 4
upcast = True
else:
element_size = q.element_size()
upcast = False
gb = 1024 ** 3
tensor_size = q.shape[0] * q.shape[1] * k.shape[1] * element_size
modifier = 3
mem_required = tensor_size * modifier
steps = 1
if mem_required > mem_free_total:
steps = 2 ** (math.ceil(math.log(mem_required / mem_free_total, 2)))
# print(f"Expected tensor size:{tensor_size/gb:0.1f}GB, cuda free:{mem_free_cuda/gb:0.1f}GB "
# f"torch free:{mem_free_torch/gb:0.1f} total:{mem_free_total/gb:0.1f} steps:{steps}")
if steps > 64:
max_res = math.floor(math.sqrt(math.sqrt(mem_free_total / 2.5)) / 8) * 64
raise RuntimeError(f'Not enough memory, use lower resolution (max approx. {max_res}x{max_res}). '
f'Need: {mem_required / 64 / gb:0.1f}GB free, Have:{mem_free_total / gb:0.1f}GB free')
if mask is not None:
if len(mask.shape) == 2:
bs = 1
else:
bs = mask.shape[0]
mask = mask.reshape(bs, -1, mask.shape[-2], mask.shape[-1]).expand(b, heads, -1, -1).reshape(-1, mask.shape[-2], mask.shape[-1])
# print("steps", steps, mem_required, mem_free_total, modifier, q.element_size(), tensor_size)
first_op_done = False
cleared_cache = False
while True:
try:
slice_size = q.shape[1] // steps if (q.shape[1] % steps) == 0 else q.shape[1]
for i in range(0, q.shape[1], slice_size):
end = i + slice_size
if upcast:
with torch.autocast(enabled=False, device_type='cuda'):
s1 = torch.einsum('b i d, b j d -> b i j', q[:, i:end].float(), k.float()) * scale
else:
s1 = torch.einsum('b i d, b j d -> b i j', q[:, i:end], k) * scale
if mask is not None:
if len(mask.shape) == 2:
s1 += mask[i:end]
else:
s1 += mask[:, i:end]
s2 = s1.softmax(dim=-1).to(v.dtype)
del s1
first_op_done = True
r1[:, i:end] = torch.einsum('b i j, b j d -> b i d', s2, v)
del s2
break
except memory_management.OOM_EXCEPTION as e:
if first_op_done == False:
memory_management.soft_empty_cache(True)
if cleared_cache == False:
cleared_cache = True
print("out of memory error, emptying cache and trying again")
continue
steps *= 2
if steps > 64:
raise e
print("out of memory error, increasing steps and trying again {}".format(steps))
else:
raise e
del q, k, v
r1 = (
r1.unsqueeze(0)
.reshape(b, heads, -1, dim_head)
.permute(0, 2, 1, 3)
.reshape(b, -1, heads * dim_head)
)
return r1
def attention_xformers(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False):
if skip_reshape:
b, _, _, dim_head = q.shape
else:
b, _, dim_head = q.shape
dim_head //= heads
if BROKEN_XFORMERS and b * heads > 65535:
return attention_pytorch(q, k, v, heads, mask, skip_reshape=skip_reshape)
if skip_reshape:
q, k, v = map(
lambda t: t.reshape(b * heads, -1, dim_head),
(q, k, v),
)
else:
q, k, v = map(
lambda t: t.reshape(b, -1, heads, dim_head),
(q, k, v),
)
if mask is not None:
pad = 8 - q.shape[1] % 8
mask_out = torch.empty([q.shape[0], q.shape[1], q.shape[1] + pad], dtype=q.dtype, device=q.device)
mask_out[:, :, :mask.shape[-1]] = mask
mask = mask_out[:, :, :mask.shape[-1]]
out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=mask)
if skip_reshape:
out = (
out.unsqueeze(0)
.reshape(b, heads, -1, dim_head)
.permute(0, 2, 1, 3)
.reshape(b, -1, heads * dim_head)
)
else:
out = (
out.reshape(b, -1, heads * dim_head)
)
return out
def attention_pytorch(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False):
if skip_reshape:
b, _, _, dim_head = q.shape
else:
b, _, dim_head = q.shape
dim_head //= heads
q, k, v = map(
lambda t: t.view(b, -1, heads, dim_head).transpose(1, 2),
(q, k, v),
)
out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False)
out = (
out.transpose(1, 2).reshape(b, -1, heads * dim_head)
)
return out
def slice_attention_single_head_spatial(q, k, v):
r1 = torch.zeros_like(k, device=q.device)
scale = (int(q.shape[-1]) ** (-0.5))
mem_free_total = memory_management.get_free_memory(q.device)
gb = 1024 ** 3
tensor_size = q.shape[0] * q.shape[1] * k.shape[2] * q.element_size()
modifier = 3 if q.element_size() == 2 else 2.5
mem_required = tensor_size * modifier
steps = 1
if mem_required > mem_free_total:
steps = 2 ** (math.ceil(math.log(mem_required / mem_free_total, 2)))
while True:
try:
slice_size = q.shape[1] // steps if (q.shape[1] % steps) == 0 else q.shape[1]
for i in range(0, q.shape[1], slice_size):
end = i + slice_size
s1 = torch.bmm(q[:, i:end], k) * scale
s2 = torch.nn.functional.softmax(s1, dim=2).permute(0, 2, 1)
del s1
r1[:, :, i:end] = torch.bmm(v, s2)
del s2
break
except memory_management.OOM_EXCEPTION as e:
memory_management.soft_empty_cache(True)
steps *= 2
if steps > 128:
raise e
print("out of memory error, increasing steps and trying again {}".format(steps))
return r1
def normal_attention_single_head_spatial(q, k, v):
# compute attention
b, c, h, w = q.shape
q = q.reshape(b, c, h * w)
q = q.permute(0, 2, 1) # b,hw,c
k = k.reshape(b, c, h * w) # b,c,hw
v = v.reshape(b, c, h * w)
r1 = slice_attention_single_head_spatial(q, k, v)
h_ = r1.reshape(b, c, h, w)
del r1
return h_
def xformers_attention_single_head_spatial(q, k, v):
# compute attention
B, C, H, W = q.shape
q, k, v = map(
lambda t: t.view(B, C, -1).transpose(1, 2).contiguous(),
(q, k, v),
)
try:
out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None)
out = out.transpose(1, 2).reshape(B, C, H, W)
except NotImplementedError as e:
out = slice_attention_single_head_spatial(q.view(B, -1, C), k.view(B, -1, C).transpose(1, 2),
v.view(B, -1, C).transpose(1, 2)).reshape(B, C, H, W)
return out
def pytorch_attention_single_head_spatial(q, k, v):
# compute attention
B, C, H, W = q.shape
q, k, v = map(
lambda t: t.view(B, 1, C, -1).transpose(2, 3).contiguous(),
(q, k, v),
)
try:
out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=0.0, is_causal=False)
out = out.transpose(2, 3).reshape(B, C, H, W)
except memory_management.OOM_EXCEPTION as e:
print("scaled_dot_product_attention OOMed: switched to slice attention")
out = slice_attention_single_head_spatial(q.view(B, -1, C), k.view(B, -1, C).transpose(1, 2),
v.view(B, -1, C).transpose(1, 2)).reshape(B, C, H, W)
return out
if memory_management.xformers_enabled():
print("Using xformers cross attention")
attention_function = attention_xformers
elif memory_management.pytorch_attention_enabled():
print("Using pytorch cross attention")
attention_function = attention_pytorch
elif args.attention_split:
print("Using split optimization for cross attention")
attention_function = attention_split
else:
print("Using sub quadratic optimization for cross attention")
attention_function = attention_sub_quad
if memory_management.xformers_enabled_vae():
print("Using xformers attention for VAE")
attention_function_single_head_spatial = xformers_attention_single_head_spatial
elif memory_management.pytorch_attention_enabled():
print("Using pytorch attention for VAE")
attention_function_single_head_spatial = pytorch_attention_single_head_spatial
else:
print("Using split attention for VAE")
attention_function_single_head_spatial = normal_attention_single_head_spatial
class AttentionProcessorForge:
def __call__(self, attn, hidden_states, encoder_hidden_states, attention_mask=None, temb=None, *args, **kwargs):
residual = hidden_states
if attn.spatial_norm is not None:
hidden_states = attn.spatial_norm(hidden_states, temb)
input_ndim = hidden_states.ndim
if input_ndim == 4:
batch_size, channel, height, width = hidden_states.shape
hidden_states = hidden_states.view(batch_size, channel, height * width).transpose(1, 2)
batch_size, sequence_length, _ = (
hidden_states.shape if encoder_hidden_states is None else encoder_hidden_states.shape
)
if attention_mask is not None:
attention_mask = attn.prepare_attention_mask(attention_mask, sequence_length, batch_size)
attention_mask = attention_mask.view(batch_size, attn.heads, -1, attention_mask.shape[-1])
if attn.group_norm is not None:
hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(1, 2)
query = attn.to_q(hidden_states)
if encoder_hidden_states is None:
encoder_hidden_states = hidden_states
elif attn.norm_cross:
encoder_hidden_states = attn.norm_encoder_hidden_states(encoder_hidden_states)
key = attn.to_k(encoder_hidden_states)
value = attn.to_v(encoder_hidden_states)
hidden_states = attention_function(query, key, value, heads=attn.heads, mask=attention_mask)
hidden_states = attn.to_out[0](hidden_states)
hidden_states = attn.to_out[1](hidden_states)
if input_ndim == 4:
hidden_states = hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
if attn.residual_connection:
hidden_states = hidden_states + residual
hidden_states = hidden_states / attn.rescale_output_factor
return hidden_states
================================================
FILE: backend/diffusion_engine/base.py
================================================
import torch
import safetensors.torch as sf
from backend import utils
class ForgeObjects:
def __init__(self, unet, clip, vae, clipvision):
self.unet = unet
self.clip = clip
self.vae = vae
self.clipvision = clipvision
def shallow_copy(self):
return ForgeObjects(
self.unet,
self.clip,
self.vae,
self.clipvision
)
class ForgeDiffusionEngine:
matched_guesses = []
def __init__(self, estimated_config, huggingface_components):
self.model_config = estimated_config
self.is_inpaint = estimated_config.inpaint_model()
self.forge_objects = None
self.forge_objects_original = None
self.forge_objects_after_applying_lora = None
self.current_lora_hash = str([])
self.fix_for_webui_backward_compatibility()
def set_clip_skip(self, clip_skip):
pass
def get_first_stage_encoding(self, x):
return x # legacy code, do not change
def get_learned_conditioning(self, prompt: list[str]):
pass
def encode_first_stage(self, x):
pass
def decode_first_stage(self, x):
pass
def get_prompt_lengths_on_ui(self, prompt):
return 0, 75
def is_webui_legacy_model(self):
return self.is_sd1 or self.is_sd2 or self.is_sdxl or self.is_sd3
def fix_for_webui_backward_compatibility(self):
self.tiling_enabled = False
self.first_stage_model = None
self.cond_stage_model = None
self.use_distilled_cfg_scale = False
self.is_sd1 = False
self.is_sd2 = False
self.is_sdxl = False
self.is_sd3 = False
return
def save_unet(self, filename):
sd = utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model)
sf.save_file(sd, filename)
return filename
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='text_encoders.')
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='vae.')
)
sf.save_file(sd, filename)
return filename
================================================
FILE: backend/diffusion_engine/chroma.py
================================================
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.t5_engine import T5TextProcessingEngine
from backend.args import dynamic_args
from backend.modules.k_prediction import PredictionFlux
from backend import memory_management
class Chroma(ForgeDiffusionEngine):
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
self.is_inpaint = False
clip = CLIP(
model_dict={
't5xxl': huggingface_components['text_encoder']
},
tokenizer_dict={
't5xxl': huggingface_components['tokenizer']
}
)
vae = VAE(model=huggingface_components['vae'])
k_predictor = PredictionFlux(
mu=1.0
)
unet = UnetPatcher.from_model(
model=huggingface_components['transformer'],
diffusers_scheduler=None,
k_predictor=k_predictor,
config=estimated_config
)
self.text_processing_engine_t5 = T5TextProcessingEngine(
text_encoder=clip.cond_stage_model.t5xxl,
tokenizer=clip.tokenizer.t5xxl,
emphasis_name=dynamic_args['emphasis_name'],
min_length=1
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
def set_clip_skip(self, clip_skip):
pass
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
return self.text_processing_engine_t5(prompt)
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
token_count = len(self.text_processing_engine_t5.tokenize([prompt])[0])
return token_count, max(255, token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
================================================
FILE: backend/diffusion_engine/flux.py
================================================
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.text_processing.t5_engine import T5TextProcessingEngine
from backend.args import dynamic_args
from backend.modules.k_prediction import PredictionFlux
from backend import memory_management
class Flux(ForgeDiffusionEngine):
matched_guesses = [model_list.Flux, model_list.FluxSchnell]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
self.is_inpaint = False
clip = CLIP(
model_dict={
'clip_l': huggingface_components['text_encoder'],
't5xxl': huggingface_components['text_encoder_2']
},
tokenizer_dict={
'clip_l': huggingface_components['tokenizer'],
't5xxl': huggingface_components['tokenizer_2']
}
)
vae = VAE(model=huggingface_components['vae'])
if 'schnell' in estimated_config.huggingface_repo.lower():
k_predictor = PredictionFlux(
mu=1.0
)
else:
k_predictor = PredictionFlux(
seq_len=4096,
base_seq_len=256,
max_seq_len=4096,
base_shift=0.5,
max_shift=1.15,
)
self.use_distilled_cfg_scale = True
unet = UnetPatcher.from_model(
model=huggingface_components['transformer'],
diffusers_scheduler=None,
k_predictor=k_predictor,
config=estimated_config
)
self.text_processing_engine_l = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_l,
tokenizer=clip.tokenizer.clip_l,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_l',
embedding_expected_shape=768,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=False,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=True,
final_layer_norm=True,
)
self.text_processing_engine_t5 = T5TextProcessingEngine(
text_encoder=clip.cond_stage_model.t5xxl,
tokenizer=clip.tokenizer.t5xxl,
emphasis_name=dynamic_args['emphasis_name'],
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
def set_clip_skip(self, clip_skip):
self.text_processing_engine_l.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond_l, pooled_l = self.text_processing_engine_l(prompt)
cond_t5 = self.text_processing_engine_t5(prompt)
cond = dict(crossattn=cond_t5, vector=pooled_l)
if self.use_distilled_cfg_scale:
distilled_cfg_scale = getattr(prompt, 'distilled_cfg_scale', 3.5) or 3.5
cond['guidance'] = torch.FloatTensor([distilled_cfg_scale] * len(prompt))
print(f'Distilled CFG Scale: {distilled_cfg_scale}')
else:
print('Distilled CFG Scale will be ignored for Schnell')
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
token_count = len(self.text_processing_engine_t5.tokenize([prompt])[0])
return token_count, max(255, token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
================================================
FILE: backend/diffusion_engine/sd15.py
================================================
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.args import dynamic_args
from backend import memory_management
import safetensors.torch as sf
from backend import utils
class StableDiffusion(ForgeDiffusionEngine):
matched_guesses = [model_list.SD15]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
clip = CLIP(
model_dict={
'clip_l': huggingface_components['text_encoder']
},
tokenizer_dict={
'clip_l': huggingface_components['tokenizer']
}
)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['unet'],
diffusers_scheduler=huggingface_components['scheduler'],
config=estimated_config
)
self.text_processing_engine = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_l,
tokenizer=clip.tokenizer.clip_l,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_l',
embedding_expected_shape=768,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=False,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=False,
final_layer_norm=True,
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sd1 = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond = self.text_processing_engine(prompt)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
_, token_count = self.text_processing_engine.process_texts([prompt])
return token_count, self.text_processing_engine.get_target_prompt_token_count(token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
model_list.SD15.process_clip_state_dict_for_saving(self,
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='')
)
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='first_stage_model.')
)
sf.save_file(sd, filename)
return filename
================================================
FILE: backend/diffusion_engine/sd20.py
================================================
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.args import dynamic_args
from backend import memory_management
import safetensors.torch as sf
from backend import utils
class StableDiffusion2(ForgeDiffusionEngine):
matched_guesses = [model_list.SD20]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
clip = CLIP(
model_dict={
'clip_h': huggingface_components['text_encoder']
},
tokenizer_dict={
'clip_h': huggingface_components['tokenizer']
}
)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['unet'],
diffusers_scheduler=huggingface_components['scheduler'],
config=estimated_config
)
self.text_processing_engine = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_h,
tokenizer=clip.tokenizer.clip_h,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_h',
embedding_expected_shape=1024,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=False,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=False,
final_layer_norm=True,
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sd2 = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond = self.text_processing_engine(prompt)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
_, token_count = self.text_processing_engine.process_texts([prompt])
return token_count, self.text_processing_engine.get_target_prompt_token_count(token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
model_list.SD20.process_clip_state_dict_for_saving(self,
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='')
)
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='first_stage_model.')
)
sf.save_file(sd, filename)
return filename
================================================
FILE: backend/diffusion_engine/sd35.py
================================================
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.text_processing.t5_engine import T5TextProcessingEngine
from backend.args import dynamic_args
from backend import memory_management
from backend.modules.k_prediction import PredictionDiscreteFlow
from modules.shared import opts
## patch SD3 Class in huggingface_guess.model_list
def SD3_clip_target(self, state_dict={}):
return {'clip_l': 'text_encoder', 'clip_g': 'text_encoder_2', 't5xxl': 'text_encoder_3'}
model_list.SD3.unet_target = 'transformer'
model_list.SD3.clip_target = SD3_clip_target
## end patch
class StableDiffusion3(ForgeDiffusionEngine):
matched_guesses = [model_list.SD3]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
self.is_inpaint = False
clip = CLIP(
model_dict={
'clip_l': huggingface_components['text_encoder'],
'clip_g': huggingface_components['text_encoder_2'],
't5xxl' : huggingface_components['text_encoder_3']
},
tokenizer_dict={
'clip_l': huggingface_components['tokenizer'],
'clip_g': huggingface_components['tokenizer_2'],
't5xxl' : huggingface_components['tokenizer_3']
}
)
k_predictor = PredictionDiscreteFlow(shift=3.0)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['transformer'],
diffusers_scheduler= None,
k_predictor=k_predictor,
config=estimated_config
)
self.text_processing_engine_l = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_l,
tokenizer=clip.tokenizer.clip_l,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_l',
embedding_expected_shape=768,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=True,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=True,
final_layer_norm=False,
)
self.text_processing_engine_g = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_g,
tokenizer=clip.tokenizer.clip_g,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_g',
embedding_expected_shape=1280,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=True,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=True,
final_layer_norm=False,
)
self.text_processing_engine_t5 = T5TextProcessingEngine(
text_encoder=clip.cond_stage_model.t5xxl,
tokenizer=clip.tokenizer.t5xxl,
emphasis_name=dynamic_args['emphasis_name'],
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sd3 = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine_l.clip_skip = clip_skip
self.text_processing_engine_g.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond_g, g_pooled = self.text_processing_engine_g(prompt)
cond_l, l_pooled = self.text_processing_engine_l(prompt)
if opts.sd3_enable_t5:
cond_t5 = self.text_processing_engine_t5(prompt)
else:
cond_t5 = torch.zeros([len(prompt), 256, 4096]).to(cond_l.device)
is_negative_prompt = getattr(prompt, 'is_negative_prompt', False)
force_zero_negative_prompt = is_negative_prompt and all(x == '' for x in prompt)
if force_zero_negative_prompt:
l_pooled = torch.zeros_like(l_pooled)
g_pooled = torch.zeros_like(g_pooled)
cond_l = torch.zeros_like(cond_l)
cond_g = torch.zeros_like(cond_g)
cond_t5 = torch.zeros_like(cond_t5)
cond_lg = torch.cat([cond_l, cond_g], dim=-1)
cond_lg = torch.nn.functional.pad(cond_lg, (0, 4096 - cond_lg.shape[-1]))
cond = dict(
crossattn=torch.cat([cond_lg, cond_t5], dim=-2),
vector=torch.cat([l_pooled, g_pooled], dim=-1),
)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
token_count = len(self.text_processing_engine_t5.tokenize([prompt])[0])
return token_count, max(255, token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
================================================
FILE: backend/diffusion_engine/sdxl.py
================================================
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.args import dynamic_args
from backend import memory_management
from backend.nn.unet import Timestep
import safetensors.torch as sf
from backend import utils
from modules.shared import opts
class StableDiffusionXL(ForgeDiffusionEngine):
matched_guesses = [model_list.SDXL]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
clip = CLIP(
model_dict={
'clip_l': huggingface_components['text_encoder'],
'clip_g': huggingface_components['text_encoder_2']
},
tokenizer_dict={
'clip_l': huggingface_components['tokenizer'],
'clip_g': huggingface_components['tokenizer_2']
}
)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['unet'],
diffusers_scheduler=huggingface_components['scheduler'],
config=estimated_config
)
self.text_processing_engine_l = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_l,
tokenizer=clip.tokenizer.clip_l,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_l',
embedding_expected_shape=2048,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=False,
minimal_clip_skip=2,
clip_skip=2,
return_pooled=False,
final_layer_norm=False,
)
self.text_processing_engine_g = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_g,
tokenizer=clip.tokenizer.clip_g,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_g',
embedding_expected_shape=2048,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=True,
minimal_clip_skip=2,
clip_skip=2,
return_pooled=True,
final_layer_norm=False,
)
self.embedder = Timestep(256)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sdxl = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine_l.clip_skip = clip_skip
self.text_processing_engine_g.clip_skip = clip_skip
@torch.infe
gitextract_xvwc7sir/ ├── .eslintignore ├── .eslintrc.js ├── .git-blame-ignore-revs ├── .gitignore ├── .pylintrc ├── CHANGELOG.md ├── CITATION.cff ├── CODEOWNERS ├── LICENSE.txt ├── NEWS.md ├── README.md ├── _typos.toml ├── backend/ │ ├── README.md │ ├── args.py │ ├── attention.py │ ├── diffusion_engine/ │ │ ├── base.py │ │ ├── chroma.py │ │ ├── flux.py │ │ ├── sd15.py │ │ ├── sd20.py │ │ ├── sd35.py │ │ └── sdxl.py │ ├── huggingface/ │ │ ├── Chroma/ │ │ │ ├── model_index.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ ├── config.json │ │ │ │ └── model.safetensors.index.json │ │ │ ├── tokenizer/ │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer.json │ │ │ │ └── tokenizer_config.json │ │ │ └── vae/ │ │ │ └── config.json │ │ ├── Kwai-Kolors/ │ │ │ └── Kolors/ │ │ │ ├── model_index.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ ├── config.json │ │ │ │ ├── pytorch_model.bin.index.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.txt │ │ │ ├── tokenizer/ │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.txt │ │ │ ├── unet/ │ │ │ │ └── config.json │ │ │ └── vae/ │ │ │ └── config.json │ │ ├── Tencent-Hunyuan/ │ │ │ └── HunyuanDiT-Diffusers/ │ │ │ ├── model_index.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ └── config.json │ │ │ ├── text_encoder_2/ │ │ │ │ ├── config.json │ │ │ │ └── model.safetensors.index.json │ │ │ ├── tokenizer/ │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.txt │ │ │ ├── tokenizer_2/ │ │ │ │ ├── special_tokens_map.json │ │ │ │ └── tokenizer_config.json │ │ │ ├── transformer/ │ │ │ │ └── config.json │ │ │ └── vae/ │ │ │ └── config.json │ │ ├── black-forest-labs/ │ │ │ ├── FLUX.1-dev/ │ │ │ │ ├── model_index.json │ │ │ │ ├── scheduler/ │ │ │ │ │ └── scheduler_config.json │ │ │ │ ├── text_encoder/ │ │ │ │ │ └── config.json │ │ │ │ ├── text_encoder_2/ │ │ │ │ │ ├── config.json │ │ │ │ │ └── model.safetensors.index.json │ │ │ │ ├── tokenizer/ │ │ │ │ │ ├── merges.txt │ │ │ │ │ ├── special_tokens_map.json │ │ │ │ │ ├── tokenizer_config.json │ │ │ │ │ └── vocab.json │ │ │ │ ├── tokenizer_2/ │ │ │ │ │ ├── special_tokens_map.json │ │ │ │ │ ├── tokenizer.json │ │ │ │ │ └── tokenizer_config.json │ │ │ │ ├── transformer/ │ │ │ │ │ ├── config.json │ │ │ │ │ └── diffusion_pytorch_model.safetensors.index.json │ │ │ │ └── vae/ │ │ │ │ └── config.json │ │ │ └── FLUX.1-schnell/ │ │ │ ├── model_index.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ └── config.json │ │ │ ├── text_encoder_2/ │ │ │ │ ├── config.json │ │ │ │ └── model.safetensors.index.json │ │ │ ├── tokenizer/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── tokenizer_2/ │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer.json │ │ │ │ └── tokenizer_config.json │ │ │ ├── transformer/ │ │ │ │ ├── config.json │ │ │ │ └── diffusion_pytorch_model.safetensors.index.json │ │ │ └── vae/ │ │ │ └── config.json │ │ ├── diffusers/ │ │ │ └── stable-diffusion-xl-1.0-inpainting-0.1/ │ │ │ ├── model_index.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ └── config.json │ │ │ ├── text_encoder_2/ │ │ │ │ └── config.json │ │ │ ├── tokenizer/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── tokenizer_2/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── unet/ │ │ │ │ └── config.json │ │ │ └── vae/ │ │ │ └── config.json │ │ ├── lllyasviel/ │ │ │ └── control_v11p_sd15_canny/ │ │ │ └── config.json │ │ ├── playgroundai/ │ │ │ └── playground-v2.5-1024px-aesthetic/ │ │ │ ├── model_index.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ └── config.json │ │ │ ├── text_encoder_2/ │ │ │ │ └── config.json │ │ │ ├── tokenizer/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── tokenizer_2/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── unet/ │ │ │ │ └── config.json │ │ │ └── vae/ │ │ │ └── config.json │ │ ├── runwayml/ │ │ │ ├── stable-diffusion-inpainting/ │ │ │ │ ├── config.json │ │ │ │ ├── feature_extractor/ │ │ │ │ │ └── preprocessor_config.json │ │ │ │ ├── model_index.json │ │ │ │ ├── safety_checker/ │ │ │ │ │ └── config.json │ │ │ │ ├── scheduler/ │ │ │ │ │ └── scheduler_config.json │ │ │ │ ├── text_encoder/ │ │ │ │ │ └── config.json │ │ │ │ ├── tokenizer/ │ │ │ │ │ ├── merges.txt │ │ │ │ │ ├── special_tokens_map.json │ │ │ │ │ ├── tokenizer_config.json │ │ │ │ │ └── vocab.json │ │ │ │ ├── unet/ │ │ │ │ │ └── config.json │ │ │ │ └── vae/ │ │ │ │ └── config.json │ │ │ └── stable-diffusion-v1-5/ │ │ │ ├── feature_extractor/ │ │ │ │ └── preprocessor_config.json │ │ │ ├── model_index.json │ │ │ ├── safety_checker/ │ │ │ │ └── config.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ └── config.json │ │ │ ├── tokenizer/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── unet/ │ │ │ │ └── config.json │ │ │ └── vae/ │ │ │ └── config.json │ │ └── stabilityai/ │ │ ├── stable-cascade/ │ │ │ ├── decoder/ │ │ │ │ └── config.json │ │ │ ├── decoder_lite/ │ │ │ │ └── config.json │ │ │ ├── model_index.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ └── config.json │ │ │ ├── tokenizer/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ └── vqgan/ │ │ │ └── config.json │ │ ├── stable-cascade-prior/ │ │ │ ├── feature_extractor/ │ │ │ │ └── preprocessor_config.json │ │ │ ├── image_encoder/ │ │ │ │ └── config.json │ │ │ ├── model_index.json │ │ │ ├── prior/ │ │ │ │ └── config.json │ │ │ ├── prior_lite/ │ │ │ │ └── config.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ └── config.json │ │ │ └── tokenizer/ │ │ │ ├── merges.txt │ │ │ ├── special_tokens_map.json │ │ │ ├── tokenizer.json │ │ │ ├── tokenizer_config.json │ │ │ └── vocab.json │ │ ├── stable-diffusion-2-1/ │ │ │ ├── feature_extractor/ │ │ │ │ └── preprocessor_config.json │ │ │ ├── model_index.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ └── config.json │ │ │ ├── tokenizer/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── unet/ │ │ │ │ └── config.json │ │ │ └── vae/ │ │ │ └── config.json │ │ ├── stable-diffusion-2-inpainting/ │ │ │ ├── feature_extractor/ │ │ │ │ └── preprocessor_config.json │ │ │ ├── model_index.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ └── config.json │ │ │ ├── tokenizer/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── unet/ │ │ │ │ └── config.json │ │ │ └── vae/ │ │ │ └── config.json │ │ ├── stable-diffusion-3-medium-diffusers/ │ │ │ ├── model_index.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ └── config.json │ │ │ ├── text_encoder_2/ │ │ │ │ └── config.json │ │ │ ├── text_encoder_3/ │ │ │ │ ├── config.json │ │ │ │ ├── model.safetensors.index.fp16.json │ │ │ │ └── model.safetensors.index.json │ │ │ ├── tokenizer/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── tokenizer_2/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── tokenizer_3/ │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── spiece.model │ │ │ │ ├── tokenizer.json │ │ │ │ └── tokenizer_config.json │ │ │ ├── transformer/ │ │ │ │ └── config.json │ │ │ └── vae/ │ │ │ └── config.json │ │ ├── stable-diffusion-x4-upscaler/ │ │ │ ├── low_res_scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── model_index.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ └── config.json │ │ │ ├── tokenizer/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── unet/ │ │ │ │ ├── .ipynb_checkpoints/ │ │ │ │ │ └── config-checkpoint.json │ │ │ │ └── config.json │ │ │ └── vae/ │ │ │ └── config.json │ │ ├── stable-diffusion-xl-base-1.0/ │ │ │ ├── model_index.json │ │ │ ├── scheduler/ │ │ │ │ └── scheduler_config.json │ │ │ ├── text_encoder/ │ │ │ │ └── config.json │ │ │ ├── text_encoder_2/ │ │ │ │ └── config.json │ │ │ ├── tokenizer/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── tokenizer_2/ │ │ │ │ ├── merges.txt │ │ │ │ ├── special_tokens_map.json │ │ │ │ ├── tokenizer_config.json │ │ │ │ └── vocab.json │ │ │ ├── unet/ │ │ │ │ └── config.json │ │ │ ├── vae/ │ │ │ │ └── config.json │ │ │ ├── vae_1_0/ │ │ │ │ └── config.json │ │ │ ├── vae_decoder/ │ │ │ │ └── config.json │ │ │ └── vae_encoder/ │ │ │ └── config.json │ │ └── stable-diffusion-xl-refiner-1.0/ │ │ ├── model_index.json │ │ ├── scheduler/ │ │ │ └── scheduler_config.json │ │ ├── text_encoder/ │ │ │ └── config.json │ │ ├── tokenizer/ │ │ │ ├── merges.txt │ │ │ ├── special_tokens_map.json │ │ │ ├── tokenizer_config.json │ │ │ └── vocab.json │ │ ├── unet/ │ │ │ └── config.json │ │ ├── vae/ │ │ │ └── config.json │ │ └── vae_1_0/ │ │ └── config.json │ ├── loader.py │ ├── memory_management.py │ ├── misc/ │ │ ├── checkpoint_pickle.py │ │ ├── diffusers_state_dict.py │ │ ├── image_resize.py │ │ ├── sub_quadratic_attention.py │ │ └── tomesd.py │ ├── modules/ │ │ ├── k_diffusion_extra.py │ │ ├── k_model.py │ │ └── k_prediction.py │ ├── nn/ │ │ ├── base.py │ │ ├── chroma.py │ │ ├── clip.py │ │ ├── cnets/ │ │ │ ├── cldm.py │ │ │ └── t2i_adapter.py │ │ ├── flux.py │ │ ├── mmditx.py │ │ ├── t5.py │ │ ├── unet.py │ │ └── vae.py │ ├── operations.py │ ├── operations_bnb.py │ ├── operations_gguf.py │ ├── patcher/ │ │ ├── base.py │ │ ├── clip.py │ │ ├── clipvision.py │ │ ├── controlnet.py │ │ ├── lora.py │ │ ├── unet.py │ │ └── vae.py │ ├── sampling/ │ │ ├── condition.py │ │ └── sampling_function.py │ ├── shared.py │ ├── state_dict.py │ ├── stream.py │ ├── text_processing/ │ │ ├── classic_engine.py │ │ ├── emphasis.py │ │ ├── parsing.py │ │ ├── t5_engine.py │ │ └── textual_inversion.py │ └── utils.py ├── download_supported_configs.py ├── environment-wsl2.yaml ├── extensions-builtin/ │ ├── ScuNET/ │ │ ├── preload.py │ │ └── scripts/ │ │ └── scunet_model.py │ ├── SwinIR/ │ │ ├── preload.py │ │ └── scripts/ │ │ └── swinir_model.py │ ├── extra-options-section/ │ │ └── scripts/ │ │ └── extra_options_section.py │ ├── forge_legacy_preprocessors/ │ │ ├── .gitignore │ │ ├── LICENSE │ │ ├── annotator/ │ │ │ ├── anime_face_segment/ │ │ │ │ ├── LICENSE │ │ │ │ └── __init__.py │ │ │ ├── annotator_path.py │ │ │ ├── binary/ │ │ │ │ └── __init__.py │ │ │ ├── canny/ │ │ │ │ └── __init__.py │ │ │ ├── color/ │ │ │ │ └── __init__.py │ │ │ ├── densepose/ │ │ │ │ ├── __init__.py │ │ │ │ └── densepose.py │ │ │ ├── depth_anything.py │ │ │ ├── depth_anything_v2.py │ │ │ ├── hed/ │ │ │ │ └── __init__.py │ │ │ ├── keypose/ │ │ │ │ ├── __init__.py │ │ │ │ ├── faster_rcnn_r50_fpn_coco.py │ │ │ │ └── hrnet_w48_coco_256x192.py │ │ │ ├── leres/ │ │ │ │ ├── __init__.py │ │ │ │ ├── leres/ │ │ │ │ │ ├── LICENSE │ │ │ │ │ ├── Resnet.py │ │ │ │ │ ├── Resnext_torch.py │ │ │ │ │ ├── depthmap.py │ │ │ │ │ ├── multi_depth_model_woauxi.py │ │ │ │ │ ├── net_tools.py │ │ │ │ │ └── network_auxi.py │ │ │ │ └── pix2pix/ │ │ │ │ ├── LICENSE │ │ │ │ ├── models/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── base_model.py │ │ │ │ │ ├── base_model_hg.py │ │ │ │ │ ├── networks.py │ │ │ │ │ └── pix2pix4depth_model.py │ │ │ │ ├── options/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── base_options.py │ │ │ │ │ └── test_options.py │ │ │ │ └── util/ │ │ │ │ ├── __init__.py │ │ │ │ ├── get_data.py │ │ │ │ ├── guidedfilter.py │ │ │ │ ├── html.py │ │ │ │ ├── image_pool.py │ │ │ │ ├── util.py │ │ │ │ └── visualizer.py │ │ │ ├── lineart/ │ │ │ │ ├── LICENSE │ │ │ │ └── __init__.py │ │ │ ├── lineart_anime/ │ │ │ │ ├── LICENSE │ │ │ │ └── __init__.py │ │ │ ├── manga_line/ │ │ │ │ ├── LICENSE │ │ │ │ └── __init__.py │ │ │ ├── mediapipe_face/ │ │ │ │ ├── __init__.py │ │ │ │ └── mediapipe_face_common.py │ │ │ ├── midas/ │ │ │ │ ├── LICENSE │ │ │ │ ├── __init__.py │ │ │ │ ├── api.py │ │ │ │ ├── midas/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── base_model.py │ │ │ │ │ ├── blocks.py │ │ │ │ │ ├── dpt_depth.py │ │ │ │ │ ├── midas_net.py │ │ │ │ │ ├── midas_net_custom.py │ │ │ │ │ ├── transforms.py │ │ │ │ │ └── vit.py │ │ │ │ └── utils.py │ │ │ ├── mlsd/ │ │ │ │ ├── LICENSE │ │ │ │ ├── __init__.py │ │ │ │ ├── models/ │ │ │ │ │ ├── mbv2_mlsd_large.py │ │ │ │ │ └── mbv2_mlsd_tiny.py │ │ │ │ └── utils.py │ │ │ ├── mmpkg/ │ │ │ │ ├── mmcv/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── arraymisc/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ └── quantization.py │ │ │ │ │ ├── cnn/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── alexnet.py │ │ │ │ │ │ ├── bricks/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── activation.py │ │ │ │ │ │ │ ├── context_block.py │ │ │ │ │ │ │ ├── conv.py │ │ │ │ │ │ │ ├── conv2d_adaptive_padding.py │ │ │ │ │ │ │ ├── conv_module.py │ │ │ │ │ │ │ ├── conv_ws.py │ │ │ │ │ │ │ ├── depthwise_separable_conv_module.py │ │ │ │ │ │ │ ├── drop.py │ │ │ │ │ │ │ ├── generalized_attention.py │ │ │ │ │ │ │ ├── hsigmoid.py │ │ │ │ │ │ │ ├── hswish.py │ │ │ │ │ │ │ ├── non_local.py │ │ │ │ │ │ │ ├── norm.py │ │ │ │ │ │ │ ├── padding.py │ │ │ │ │ │ │ ├── plugin.py │ │ │ │ │ │ │ ├── registry.py │ │ │ │ │ │ │ ├── scale.py │ │ │ │ │ │ │ ├── swish.py │ │ │ │ │ │ │ ├── transformer.py │ │ │ │ │ │ │ ├── upsample.py │ │ │ │ │ │ │ └── wrappers.py │ │ │ │ │ │ ├── builder.py │ │ │ │ │ │ ├── resnet.py │ │ │ │ │ │ ├── utils/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── flops_counter.py │ │ │ │ │ │ │ ├── fuse_conv_bn.py │ │ │ │ │ │ │ ├── sync_bn.py │ │ │ │ │ │ │ └── weight_init.py │ │ │ │ │ │ └── vgg.py │ │ │ │ │ ├── engine/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ └── test.py │ │ │ │ │ ├── fileio/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── file_client.py │ │ │ │ │ │ ├── handlers/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── base.py │ │ │ │ │ │ │ ├── json_handler.py │ │ │ │ │ │ │ ├── pickle_handler.py │ │ │ │ │ │ │ └── yaml_handler.py │ │ │ │ │ │ ├── io.py │ │ │ │ │ │ └── parse.py │ │ │ │ │ ├── image/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── colorspace.py │ │ │ │ │ │ ├── geometric.py │ │ │ │ │ │ ├── io.py │ │ │ │ │ │ ├── misc.py │ │ │ │ │ │ └── photometric.py │ │ │ │ │ ├── model_zoo/ │ │ │ │ │ │ ├── deprecated.json │ │ │ │ │ │ ├── mmcls.json │ │ │ │ │ │ └── open_mmlab.json │ │ │ │ │ ├── ops/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── assign_score_withk.py │ │ │ │ │ │ ├── ball_query.py │ │ │ │ │ │ ├── bbox.py │ │ │ │ │ │ ├── border_align.py │ │ │ │ │ │ ├── box_iou_rotated.py │ │ │ │ │ │ ├── carafe.py │ │ │ │ │ │ ├── cc_attention.py │ │ │ │ │ │ ├── contour_expand.py │ │ │ │ │ │ ├── corner_pool.py │ │ │ │ │ │ ├── correlation.py │ │ │ │ │ │ ├── deform_conv.py │ │ │ │ │ │ ├── deform_roi_pool.py │ │ │ │ │ │ ├── deprecated_wrappers.py │ │ │ │ │ │ ├── focal_loss.py │ │ │ │ │ │ ├── furthest_point_sample.py │ │ │ │ │ │ ├── fused_bias_leakyrelu.py │ │ │ │ │ │ ├── gather_points.py │ │ │ │ │ │ ├── group_points.py │ │ │ │ │ │ ├── info.py │ │ │ │ │ │ ├── iou3d.py │ │ │ │ │ │ ├── knn.py │ │ │ │ │ │ ├── masked_conv.py │ │ │ │ │ │ ├── merge_cells.py │ │ │ │ │ │ ├── modulated_deform_conv.py │ │ │ │ │ │ ├── multi_scale_deform_attn.py │ │ │ │ │ │ ├── nms.py │ │ │ │ │ │ ├── pixel_group.py │ │ │ │ │ │ ├── point_sample.py │ │ │ │ │ │ ├── points_in_boxes.py │ │ │ │ │ │ ├── points_sampler.py │ │ │ │ │ │ ├── psa_mask.py │ │ │ │ │ │ ├── roi_align.py │ │ │ │ │ │ ├── roi_align_rotated.py │ │ │ │ │ │ ├── roi_pool.py │ │ │ │ │ │ ├── roiaware_pool3d.py │ │ │ │ │ │ ├── roipoint_pool3d.py │ │ │ │ │ │ ├── saconv.py │ │ │ │ │ │ ├── scatter_points.py │ │ │ │ │ │ ├── sync_bn.py │ │ │ │ │ │ ├── three_interpolate.py │ │ │ │ │ │ ├── three_nn.py │ │ │ │ │ │ ├── tin_shift.py │ │ │ │ │ │ ├── upfirdn2d.py │ │ │ │ │ │ └── voxelize.py │ │ │ │ │ ├── parallel/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── _functions.py │ │ │ │ │ │ ├── collate.py │ │ │ │ │ │ ├── data_container.py │ │ │ │ │ │ ├── data_parallel.py │ │ │ │ │ │ ├── distributed.py │ │ │ │ │ │ ├── distributed_deprecated.py │ │ │ │ │ │ ├── registry.py │ │ │ │ │ │ ├── scatter_gather.py │ │ │ │ │ │ └── utils.py │ │ │ │ │ ├── runner/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── base_module.py │ │ │ │ │ │ ├── base_runner.py │ │ │ │ │ │ ├── builder.py │ │ │ │ │ │ ├── checkpoint.py │ │ │ │ │ │ ├── default_constructor.py │ │ │ │ │ │ ├── dist_utils.py │ │ │ │ │ │ ├── epoch_based_runner.py │ │ │ │ │ │ ├── fp16_utils.py │ │ │ │ │ │ ├── hooks/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── checkpoint.py │ │ │ │ │ │ │ ├── closure.py │ │ │ │ │ │ │ ├── ema.py │ │ │ │ │ │ │ ├── evaluation.py │ │ │ │ │ │ │ ├── hook.py │ │ │ │ │ │ │ ├── iter_timer.py │ │ │ │ │ │ │ ├── logger/ │ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ │ ├── base.py │ │ │ │ │ │ │ │ ├── dvclive.py │ │ │ │ │ │ │ │ ├── mlflow.py │ │ │ │ │ │ │ │ ├── neptune.py │ │ │ │ │ │ │ │ ├── pavi.py │ │ │ │ │ │ │ │ ├── tensorboard.py │ │ │ │ │ │ │ │ ├── text.py │ │ │ │ │ │ │ │ └── wandb.py │ │ │ │ │ │ │ ├── lr_updater.py │ │ │ │ │ │ │ ├── memory.py │ │ │ │ │ │ │ ├── momentum_updater.py │ │ │ │ │ │ │ ├── optimizer.py │ │ │ │ │ │ │ ├── profiler.py │ │ │ │ │ │ │ ├── sampler_seed.py │ │ │ │ │ │ │ └── sync_buffer.py │ │ │ │ │ │ ├── iter_based_runner.py │ │ │ │ │ │ ├── log_buffer.py │ │ │ │ │ │ ├── optimizer/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── builder.py │ │ │ │ │ │ │ └── default_constructor.py │ │ │ │ │ │ ├── priority.py │ │ │ │ │ │ └── utils.py │ │ │ │ │ ├── utils/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── config.py │ │ │ │ │ │ ├── env.py │ │ │ │ │ │ ├── ext_loader.py │ │ │ │ │ │ ├── logging.py │ │ │ │ │ │ ├── misc.py │ │ │ │ │ │ ├── parrots_jit.py │ │ │ │ │ │ ├── parrots_wrapper.py │ │ │ │ │ │ ├── path.py │ │ │ │ │ │ ├── progressbar.py │ │ │ │ │ │ ├── registry.py │ │ │ │ │ │ ├── testing.py │ │ │ │ │ │ ├── timer.py │ │ │ │ │ │ ├── trace.py │ │ │ │ │ │ └── version_utils.py │ │ │ │ │ ├── version.py │ │ │ │ │ ├── video/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── io.py │ │ │ │ │ │ ├── optflow.py │ │ │ │ │ │ └── processing.py │ │ │ │ │ └── visualization/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── color.py │ │ │ │ │ ├── image.py │ │ │ │ │ └── optflow.py │ │ │ │ └── mmseg/ │ │ │ │ ├── apis/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── inference.py │ │ │ │ │ ├── test.py │ │ │ │ │ └── train.py │ │ │ │ ├── core/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── evaluation/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── class_names.py │ │ │ │ │ │ ├── eval_hooks.py │ │ │ │ │ │ └── metrics.py │ │ │ │ │ ├── seg/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── builder.py │ │ │ │ │ │ └── sampler/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── base_pixel_sampler.py │ │ │ │ │ │ └── ohem_pixel_sampler.py │ │ │ │ │ └── utils/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ └── misc.py │ │ │ │ ├── datasets/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── ade.py │ │ │ │ │ ├── builder.py │ │ │ │ │ ├── chase_db1.py │ │ │ │ │ ├── cityscapes.py │ │ │ │ │ ├── custom.py │ │ │ │ │ ├── dataset_wrappers.py │ │ │ │ │ ├── drive.py │ │ │ │ │ ├── hrf.py │ │ │ │ │ ├── pascal_context.py │ │ │ │ │ ├── pipelines/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── compose.py │ │ │ │ │ │ ├── formating.py │ │ │ │ │ │ ├── loading.py │ │ │ │ │ │ ├── test_time_aug.py │ │ │ │ │ │ └── transforms.py │ │ │ │ │ ├── stare.py │ │ │ │ │ └── voc.py │ │ │ │ ├── models/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── backbones/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── cgnet.py │ │ │ │ │ │ ├── fast_scnn.py │ │ │ │ │ │ ├── hrnet.py │ │ │ │ │ │ ├── mobilenet_v2.py │ │ │ │ │ │ ├── mobilenet_v3.py │ │ │ │ │ │ ├── resnest.py │ │ │ │ │ │ ├── resnet.py │ │ │ │ │ │ ├── resnext.py │ │ │ │ │ │ ├── unet.py │ │ │ │ │ │ └── vit.py │ │ │ │ │ ├── builder.py │ │ │ │ │ ├── decode_heads/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── ann_head.py │ │ │ │ │ │ ├── apc_head.py │ │ │ │ │ │ ├── aspp_head.py │ │ │ │ │ │ ├── cascade_decode_head.py │ │ │ │ │ │ ├── cc_head.py │ │ │ │ │ │ ├── da_head.py │ │ │ │ │ │ ├── decode_head.py │ │ │ │ │ │ ├── dm_head.py │ │ │ │ │ │ ├── dnl_head.py │ │ │ │ │ │ ├── ema_head.py │ │ │ │ │ │ ├── enc_head.py │ │ │ │ │ │ ├── fcn_head.py │ │ │ │ │ │ ├── fpn_head.py │ │ │ │ │ │ ├── gc_head.py │ │ │ │ │ │ ├── lraspp_head.py │ │ │ │ │ │ ├── nl_head.py │ │ │ │ │ │ ├── ocr_head.py │ │ │ │ │ │ ├── point_head.py │ │ │ │ │ │ ├── psa_head.py │ │ │ │ │ │ ├── psp_head.py │ │ │ │ │ │ ├── sep_aspp_head.py │ │ │ │ │ │ ├── sep_fcn_head.py │ │ │ │ │ │ └── uper_head.py │ │ │ │ │ ├── losses/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── accuracy.py │ │ │ │ │ │ ├── cross_entropy_loss.py │ │ │ │ │ │ ├── dice_loss.py │ │ │ │ │ │ ├── lovasz_loss.py │ │ │ │ │ │ └── utils.py │ │ │ │ │ ├── necks/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── fpn.py │ │ │ │ │ │ └── multilevel_neck.py │ │ │ │ │ ├── segmentors/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── base.py │ │ │ │ │ │ ├── cascade_encoder_decoder.py │ │ │ │ │ │ └── encoder_decoder.py │ │ │ │ │ └── utils/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── drop.py │ │ │ │ │ ├── inverted_residual.py │ │ │ │ │ ├── make_divisible.py │ │ │ │ │ ├── res_layer.py │ │ │ │ │ ├── se_layer.py │ │ │ │ │ ├── self_attention_block.py │ │ │ │ │ ├── up_conv_block.py │ │ │ │ │ └── weight_init.py │ │ │ │ ├── ops/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── encoding.py │ │ │ │ │ └── wrappers.py │ │ │ │ └── utils/ │ │ │ │ ├── __init__.py │ │ │ │ ├── collect_env.py │ │ │ │ └── logger.py │ │ │ ├── oneformer/ │ │ │ │ ├── LICENSE │ │ │ │ ├── __init__.py │ │ │ │ ├── api.py │ │ │ │ ├── configs/ │ │ │ │ │ ├── ade20k/ │ │ │ │ │ │ ├── Base-ADE20K-UnifiedSegmentation.yaml │ │ │ │ │ │ ├── oneformer_R50_bs16_160k.yaml │ │ │ │ │ │ └── oneformer_swin_large_IN21k_384_bs16_160k.yaml │ │ │ │ │ └── coco/ │ │ │ │ │ ├── Base-COCO-UnifiedSegmentation.yaml │ │ │ │ │ ├── oneformer_R50_bs16_50ep.yaml │ │ │ │ │ └── oneformer_swin_large_IN21k_384_bs16_100ep.yaml │ │ │ │ ├── detectron2/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── checkpoint/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── c2_model_loading.py │ │ │ │ │ │ ├── catalog.py │ │ │ │ │ │ └── detection_checkpoint.py │ │ │ │ │ ├── config/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── compat.py │ │ │ │ │ │ ├── config.py │ │ │ │ │ │ ├── defaults.py │ │ │ │ │ │ ├── instantiate.py │ │ │ │ │ │ └── lazy.py │ │ │ │ │ ├── data/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── benchmark.py │ │ │ │ │ │ ├── build.py │ │ │ │ │ │ ├── catalog.py │ │ │ │ │ │ ├── common.py │ │ │ │ │ │ ├── dataset_mapper.py │ │ │ │ │ │ ├── datasets/ │ │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── builtin.py │ │ │ │ │ │ │ ├── builtin_meta.py │ │ │ │ │ │ │ ├── cityscapes.py │ │ │ │ │ │ │ ├── cityscapes_panoptic.py │ │ │ │ │ │ │ ├── coco.py │ │ │ │ │ │ │ ├── coco_panoptic.py │ │ │ │ │ │ │ ├── lvis.py │ │ │ │ │ │ │ ├── lvis_v0_5_categories.py │ │ │ │ │ │ │ ├── lvis_v1_categories.py │ │ │ │ │ │ │ ├── lvis_v1_category_image_count.py │ │ │ │ │ │ │ ├── pascal_voc.py │ │ │ │ │ │ │ └── register_coco.py │ │ │ │ │ │ ├── detection_utils.py │ │ │ │ │ │ ├── samplers/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── distributed_sampler.py │ │ │ │ │ │ │ └── grouped_batch_sampler.py │ │ │ │ │ │ └── transforms/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── augmentation.py │ │ │ │ │ │ ├── augmentation_impl.py │ │ │ │ │ │ └── transform.py │ │ │ │ │ ├── engine/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── defaults.py │ │ │ │ │ │ ├── hooks.py │ │ │ │ │ │ ├── launch.py │ │ │ │ │ │ └── train_loop.py │ │ │ │ │ ├── evaluation/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── cityscapes_evaluation.py │ │ │ │ │ │ ├── coco_evaluation.py │ │ │ │ │ │ ├── evaluator.py │ │ │ │ │ │ ├── fast_eval_api.py │ │ │ │ │ │ ├── lvis_evaluation.py │ │ │ │ │ │ ├── panoptic_evaluation.py │ │ │ │ │ │ ├── pascal_voc_evaluation.py │ │ │ │ │ │ ├── rotated_coco_evaluation.py │ │ │ │ │ │ ├── sem_seg_evaluation.py │ │ │ │ │ │ └── testing.py │ │ │ │ │ ├── export/ │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── api.py │ │ │ │ │ │ ├── c10.py │ │ │ │ │ │ ├── caffe2_export.py │ │ │ │ │ │ ├── caffe2_inference.py │ │ │ │ │ │ ├── caffe2_modeling.py │ │ │ │ │ │ ├── caffe2_patch.py │ │ │ │ │ │ ├── flatten.py │ │ │ │ │ │ ├── shared.py │ │ │ │ │ │ ├── torchscript.py │ │ │ │ │ │ └── torchscript_patch.py │ │ │ │ │ ├── layers/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── aspp.py │ │ │ │ │ │ ├── batch_norm.py │ │ │ │ │ │ ├── blocks.py │ │ │ │ │ │ ├── csrc/ │ │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ │ ├── ROIAlignRotated/ │ │ │ │ │ │ │ │ ├── ROIAlignRotated.h │ │ │ │ │ │ │ │ ├── ROIAlignRotated_cpu.cpp │ │ │ │ │ │ │ │ └── ROIAlignRotated_cuda.cu │ │ │ │ │ │ │ ├── box_iou_rotated/ │ │ │ │ │ │ │ │ ├── box_iou_rotated.h │ │ │ │ │ │ │ │ ├── box_iou_rotated_cpu.cpp │ │ │ │ │ │ │ │ ├── box_iou_rotated_cuda.cu │ │ │ │ │ │ │ │ └── box_iou_rotated_utils.h │ │ │ │ │ │ │ ├── cocoeval/ │ │ │ │ │ │ │ │ ├── cocoeval.cpp │ │ │ │ │ │ │ │ └── cocoeval.h │ │ │ │ │ │ │ ├── cuda_version.cu │ │ │ │ │ │ │ ├── deformable/ │ │ │ │ │ │ │ │ ├── deform_conv.h │ │ │ │ │ │ │ │ ├── deform_conv_cuda.cu │ │ │ │ │ │ │ │ └── deform_conv_cuda_kernel.cu │ │ │ │ │ │ │ ├── nms_rotated/ │ │ │ │ │ │ │ │ ├── nms_rotated.h │ │ │ │ │ │ │ │ ├── nms_rotated_cpu.cpp │ │ │ │ │ │ │ │ └── nms_rotated_cuda.cu │ │ │ │ │ │ │ └── vision.cpp │ │ │ │ │ │ ├── deform_conv.py │ │ │ │ │ │ ├── losses.py │ │ │ │ │ │ ├── mask_ops.py │ │ │ │ │ │ ├── nms.py │ │ │ │ │ │ ├── roi_align.py │ │ │ │ │ │ ├── roi_align_rotated.py │ │ │ │ │ │ ├── rotated_boxes.py │ │ │ │ │ │ ├── shape_spec.py │ │ │ │ │ │ └── wrappers.py │ │ │ │ │ ├── model_zoo/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ └── model_zoo.py │ │ │ │ │ ├── modeling/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── anchor_generator.py │ │ │ │ │ │ ├── backbone/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── backbone.py │ │ │ │ │ │ │ ├── build.py │ │ │ │ │ │ │ ├── fpn.py │ │ │ │ │ │ │ ├── mvit.py │ │ │ │ │ │ │ ├── regnet.py │ │ │ │ │ │ │ ├── resnet.py │ │ │ │ │ │ │ ├── swin.py │ │ │ │ │ │ │ ├── utils.py │ │ │ │ │ │ │ └── vit.py │ │ │ │ │ │ ├── box_regression.py │ │ │ │ │ │ ├── matcher.py │ │ │ │ │ │ ├── meta_arch/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── build.py │ │ │ │ │ │ │ ├── dense_detector.py │ │ │ │ │ │ │ ├── fcos.py │ │ │ │ │ │ │ ├── panoptic_fpn.py │ │ │ │ │ │ │ ├── rcnn.py │ │ │ │ │ │ │ ├── retinanet.py │ │ │ │ │ │ │ └── semantic_seg.py │ │ │ │ │ │ ├── mmdet_wrapper.py │ │ │ │ │ │ ├── poolers.py │ │ │ │ │ │ ├── postprocessing.py │ │ │ │ │ │ ├── proposal_generator/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── build.py │ │ │ │ │ │ │ ├── proposal_utils.py │ │ │ │ │ │ │ ├── rpn.py │ │ │ │ │ │ │ └── rrpn.py │ │ │ │ │ │ ├── roi_heads/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── box_head.py │ │ │ │ │ │ │ ├── cascade_rcnn.py │ │ │ │ │ │ │ ├── fast_rcnn.py │ │ │ │ │ │ │ ├── keypoint_head.py │ │ │ │ │ │ │ ├── mask_head.py │ │ │ │ │ │ │ ├── roi_heads.py │ │ │ │ │ │ │ └── rotated_fast_rcnn.py │ │ │ │ │ │ ├── sampling.py │ │ │ │ │ │ └── test_time_augmentation.py │ │ │ │ │ ├── projects/ │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ └── deeplab/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── build_solver.py │ │ │ │ │ │ ├── config.py │ │ │ │ │ │ ├── loss.py │ │ │ │ │ │ ├── lr_scheduler.py │ │ │ │ │ │ ├── resnet.py │ │ │ │ │ │ └── semantic_seg.py │ │ │ │ │ ├── solver/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── build.py │ │ │ │ │ │ └── lr_scheduler.py │ │ │ │ │ ├── structures/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── boxes.py │ │ │ │ │ │ ├── image_list.py │ │ │ │ │ │ ├── instances.py │ │ │ │ │ │ ├── keypoints.py │ │ │ │ │ │ ├── masks.py │ │ │ │ │ │ └── rotated_boxes.py │ │ │ │ │ ├── tracking/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── base_tracker.py │ │ │ │ │ │ ├── bbox_iou_tracker.py │ │ │ │ │ │ ├── hungarian_tracker.py │ │ │ │ │ │ ├── iou_weighted_hungarian_bbox_iou_tracker.py │ │ │ │ │ │ ├── utils.py │ │ │ │ │ │ └── vanilla_hungarian_bbox_iou_tracker.py │ │ │ │ │ └── utils/ │ │ │ │ │ ├── README.md │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── analysis.py │ │ │ │ │ ├── collect_env.py │ │ │ │ │ ├── colormap.py │ │ │ │ │ ├── comm.py │ │ │ │ │ ├── develop.py │ │ │ │ │ ├── env.py │ │ │ │ │ ├── events.py │ │ │ │ │ ├── file_io.py │ │ │ │ │ ├── logger.py │ │ │ │ │ ├── memory.py │ │ │ │ │ ├── registry.py │ │ │ │ │ ├── serialize.py │ │ │ │ │ ├── testing.py │ │ │ │ │ ├── tracing.py │ │ │ │ │ ├── video_visualizer.py │ │ │ │ │ └── visualizer.py │ │ │ │ ├── oneformer/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── config.py │ │ │ │ │ ├── data/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── build.py │ │ │ │ │ │ ├── dataset_mappers/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── coco_unified_new_baseline_dataset_mapper.py │ │ │ │ │ │ │ ├── dataset_mapper.py │ │ │ │ │ │ │ └── oneformer_unified_dataset_mapper.py │ │ │ │ │ │ ├── datasets/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── register_ade20k_instance.py │ │ │ │ │ │ │ ├── register_ade20k_panoptic.py │ │ │ │ │ │ │ ├── register_cityscapes_panoptic.py │ │ │ │ │ │ │ ├── register_coco_panoptic2instance.py │ │ │ │ │ │ │ └── register_coco_panoptic_annos_semseg.py │ │ │ │ │ │ └── tokenizer.py │ │ │ │ │ ├── demo/ │ │ │ │ │ │ ├── colormap.py │ │ │ │ │ │ ├── defaults.py │ │ │ │ │ │ ├── predictor.py │ │ │ │ │ │ └── visualizer.py │ │ │ │ │ ├── evaluation/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── cityscapes_evaluation.py │ │ │ │ │ │ ├── coco_evaluator.py │ │ │ │ │ │ ├── detection_coco_evaluator.py │ │ │ │ │ │ ├── evaluator.py │ │ │ │ │ │ └── instance_evaluation.py │ │ │ │ │ ├── modeling/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── backbone/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── dinat.py │ │ │ │ │ │ │ └── swin.py │ │ │ │ │ │ ├── matcher.py │ │ │ │ │ │ ├── meta_arch/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ └── oneformer_head.py │ │ │ │ │ │ ├── pixel_decoder/ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ ├── fpn.py │ │ │ │ │ │ │ ├── msdeformattn.py │ │ │ │ │ │ │ └── ops/ │ │ │ │ │ │ │ ├── functions/ │ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ │ └── ms_deform_attn_func.py │ │ │ │ │ │ │ ├── make.sh │ │ │ │ │ │ │ ├── modules/ │ │ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ │ │ └── ms_deform_attn.py │ │ │ │ │ │ │ ├── setup.py │ │ │ │ │ │ │ ├── src/ │ │ │ │ │ │ │ │ ├── cpu/ │ │ │ │ │ │ │ │ │ ├── ms_deform_attn_cpu.cpp │ │ │ │ │ │ │ │ │ └── ms_deform_attn_cpu.h │ │ │ │ │ │ │ │ ├── cuda/ │ │ │ │ │ │ │ │ │ ├── ms_deform_attn_cuda.cu │ │ │ │ │ │ │ │ │ ├── ms_deform_attn_cuda.h │ │ │ │ │ │ │ │ │ └── ms_deform_im2col_cuda.cuh │ │ │ │ │ │ │ │ ├── ms_deform_attn.h │ │ │ │ │ │ │ │ └── vision.cpp │ │ │ │ │ │ │ └── test.py │ │ │ │ │ │ └── transformer_decoder/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── oneformer_transformer_decoder.py │ │ │ │ │ │ ├── position_encoding.py │ │ │ │ │ │ ├── text_transformer.py │ │ │ │ │ │ └── transformer.py │ │ │ │ │ ├── oneformer_model.py │ │ │ │ │ └── utils/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── box_ops.py │ │ │ │ │ ├── events.py │ │ │ │ │ ├── misc.py │ │ │ │ │ └── pos_embed.py │ │ │ │ └── pycocotools/ │ │ │ │ ├── __init__.py │ │ │ │ ├── coco.py │ │ │ │ ├── cocoeval.py │ │ │ │ └── mask.py │ │ │ ├── openpose/ │ │ │ │ ├── LICENSE │ │ │ │ ├── __init__.py │ │ │ │ ├── animalpose.py │ │ │ │ ├── body.py │ │ │ │ ├── cv_ox_det.py │ │ │ │ ├── cv_ox_pose.py │ │ │ │ ├── face.py │ │ │ │ ├── hand.py │ │ │ │ ├── model.py │ │ │ │ ├── types.py │ │ │ │ ├── util.py │ │ │ │ └── wholebody.py │ │ │ ├── pidinet/ │ │ │ │ ├── LICENSE │ │ │ │ ├── __init__.py │ │ │ │ └── model.py │ │ │ ├── shuffle/ │ │ │ │ └── __init__.py │ │ │ ├── teed/ │ │ │ │ ├── Fmish.py │ │ │ │ ├── Fsmish.py │ │ │ │ ├── LICENSE.txt │ │ │ │ ├── Xmish.py │ │ │ │ ├── Xsmish.py │ │ │ │ ├── __init__.py │ │ │ │ └── ted.py │ │ │ ├── uniformer/ │ │ │ │ ├── LICENSE │ │ │ │ ├── __init__.py │ │ │ │ ├── configs/ │ │ │ │ │ └── _base_/ │ │ │ │ │ ├── datasets/ │ │ │ │ │ │ ├── ade20k.py │ │ │ │ │ │ ├── chase_db1.py │ │ │ │ │ │ ├── cityscapes.py │ │ │ │ │ │ ├── cityscapes_769x769.py │ │ │ │ │ │ ├── drive.py │ │ │ │ │ │ ├── hrf.py │ │ │ │ │ │ ├── pascal_context.py │ │ │ │ │ │ ├── pascal_context_59.py │ │ │ │ │ │ ├── pascal_voc12.py │ │ │ │ │ │ ├── pascal_voc12_aug.py │ │ │ │ │ │ └── stare.py │ │ │ │ │ ├── default_runtime.py │ │ │ │ │ ├── models/ │ │ │ │ │ │ ├── ann_r50-d8.py │ │ │ │ │ │ ├── apcnet_r50-d8.py │ │ │ │ │ │ ├── ccnet_r50-d8.py │ │ │ │ │ │ ├── cgnet.py │ │ │ │ │ │ ├── danet_r50-d8.py │ │ │ │ │ │ ├── deeplabv3_r50-d8.py │ │ │ │ │ │ ├── deeplabv3_unet_s5-d16.py │ │ │ │ │ │ ├── deeplabv3plus_r50-d8.py │ │ │ │ │ │ ├── dmnet_r50-d8.py │ │ │ │ │ │ ├── dnl_r50-d8.py │ │ │ │ │ │ ├── emanet_r50-d8.py │ │ │ │ │ │ ├── encnet_r50-d8.py │ │ │ │ │ │ ├── fast_scnn.py │ │ │ │ │ │ ├── fcn_hr18.py │ │ │ │ │ │ ├── fcn_r50-d8.py │ │ │ │ │ │ ├── fcn_unet_s5-d16.py │ │ │ │ │ │ ├── fpn_r50.py │ │ │ │ │ │ ├── fpn_uniformer.py │ │ │ │ │ │ ├── gcnet_r50-d8.py │ │ │ │ │ │ ├── lraspp_m-v3-d8.py │ │ │ │ │ │ ├── nonlocal_r50-d8.py │ │ │ │ │ │ ├── ocrnet_hr18.py │ │ │ │ │ │ ├── ocrnet_r50-d8.py │ │ │ │ │ │ ├── pointrend_r50.py │ │ │ │ │ │ ├── psanet_r50-d8.py │ │ │ │ │ │ ├── pspnet_r50-d8.py │ │ │ │ │ │ ├── pspnet_unet_s5-d16.py │ │ │ │ │ │ ├── upernet_r50.py │ │ │ │ │ │ └── upernet_uniformer.py │ │ │ │ │ └── schedules/ │ │ │ │ │ ├── schedule_160k.py │ │ │ │ │ ├── schedule_20k.py │ │ │ │ │ ├── schedule_40k.py │ │ │ │ │ └── schedule_80k.py │ │ │ │ ├── inference.py │ │ │ │ ├── mmcv_custom/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ └── checkpoint.py │ │ │ │ ├── uniformer.py │ │ │ │ └── upernet_global_small.py │ │ │ ├── util.py │ │ │ └── zoe/ │ │ │ ├── LICENSE │ │ │ ├── __init__.py │ │ │ └── zoedepth/ │ │ │ ├── models/ │ │ │ │ ├── __init__.py │ │ │ │ ├── base_models/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── midas.py │ │ │ │ │ └── midas_repo/ │ │ │ │ │ ├── .gitignore │ │ │ │ │ ├── Dockerfile │ │ │ │ │ ├── LICENSE │ │ │ │ │ ├── README.md │ │ │ │ │ ├── environment.yaml │ │ │ │ │ ├── hubconf.py │ │ │ │ │ ├── input/ │ │ │ │ │ │ └── .placeholder │ │ │ │ │ ├── midas/ │ │ │ │ │ │ ├── backbones/ │ │ │ │ │ │ │ ├── beit.py │ │ │ │ │ │ │ ├── levit.py │ │ │ │ │ │ │ ├── next_vit.py │ │ │ │ │ │ │ ├── swin.py │ │ │ │ │ │ │ ├── swin2.py │ │ │ │ │ │ │ ├── swin_common.py │ │ │ │ │ │ │ ├── utils.py │ │ │ │ │ │ │ └── vit.py │ │ │ │ │ │ ├── base_model.py │ │ │ │ │ │ ├── blocks.py │ │ │ │ │ │ ├── dpt_depth.py │ │ │ │ │ │ ├── midas_net.py │ │ │ │ │ │ ├── midas_net_custom.py │ │ │ │ │ │ ├── model_loader.py │ │ │ │ │ │ └── transforms.py │ │ │ │ │ ├── output/ │ │ │ │ │ │ └── .placeholder │ │ │ │ │ ├── ros/ │ │ │ │ │ │ ├── LICENSE │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── additions/ │ │ │ │ │ │ │ ├── do_catkin_make.sh │ │ │ │ │ │ │ ├── downloads.sh │ │ │ │ │ │ │ ├── install_ros_melodic_ubuntu_17_18.sh │ │ │ │ │ │ │ ├── install_ros_noetic_ubuntu_20.sh │ │ │ │ │ │ │ └── make_package_cpp.sh │ │ │ │ │ │ ├── launch_midas_cpp.sh │ │ │ │ │ │ ├── midas_cpp/ │ │ │ │ │ │ │ ├── CMakeLists.txt │ │ │ │ │ │ │ ├── launch/ │ │ │ │ │ │ │ │ ├── midas_cpp.launch │ │ │ │ │ │ │ │ └── midas_talker_listener.launch │ │ │ │ │ │ │ ├── package.xml │ │ │ │ │ │ │ ├── scripts/ │ │ │ │ │ │ │ │ ├── listener.py │ │ │ │ │ │ │ │ ├── listener_original.py │ │ │ │ │ │ │ │ └── talker.py │ │ │ │ │ │ │ └── src/ │ │ │ │ │ │ │ └── main.cpp │ │ │ │ │ │ └── run_talker_listener_test.sh │ │ │ │ │ ├── run.py │ │ │ │ │ ├── tf/ │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── input/ │ │ │ │ │ │ │ └── .placeholder │ │ │ │ │ │ ├── make_onnx_model.py │ │ │ │ │ │ ├── output/ │ │ │ │ │ │ │ └── .placeholder │ │ │ │ │ │ ├── run_onnx.py │ │ │ │ │ │ ├── run_pb.py │ │ │ │ │ │ ├── transforms.py │ │ │ │ │ │ └── utils.py │ │ │ │ │ ├── utils.py │ │ │ │ │ └── weights/ │ │ │ │ │ └── .placeholder │ │ │ │ ├── builder.py │ │ │ │ ├── depth_model.py │ │ │ │ ├── layers/ │ │ │ │ │ ├── attractor.py │ │ │ │ │ ├── dist_layers.py │ │ │ │ │ ├── localbins_layers.py │ │ │ │ │ └── patch_transformer.py │ │ │ │ ├── model_io.py │ │ │ │ ├── zoedepth/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── config_zoedepth.json │ │ │ │ │ ├── config_zoedepth_kitti.json │ │ │ │ │ └── zoedepth_v1.py │ │ │ │ └── zoedepth_nk/ │ │ │ │ ├── __init__.py │ │ │ │ ├── config_zoedepth_nk.json │ │ │ │ └── zoedepth_nk_v1.py │ │ │ └── utils/ │ │ │ ├── __init__.py │ │ │ ├── arg_utils.py │ │ │ ├── config.py │ │ │ ├── easydict/ │ │ │ │ └── __init__.py │ │ │ ├── geometry.py │ │ │ └── misc.py │ │ ├── install.py │ │ ├── legacy_preprocessors/ │ │ │ ├── preprocessor.py │ │ │ └── preprocessor_compiled.py │ │ ├── requirements.txt │ │ └── scripts/ │ │ └── legacy_preprocessors.py │ ├── forge_preprocessor_inpaint/ │ │ ├── annotator/ │ │ │ └── lama/ │ │ │ └── saicinpainting/ │ │ │ ├── __init__.py │ │ │ ├── training/ │ │ │ │ ├── __init__.py │ │ │ │ ├── data/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ └── masks.py │ │ │ │ ├── losses/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── adversarial.py │ │ │ │ │ ├── constants.py │ │ │ │ │ ├── distance_weighting.py │ │ │ │ │ ├── feature_matching.py │ │ │ │ │ ├── perceptual.py │ │ │ │ │ ├── segmentation.py │ │ │ │ │ └── style_loss.py │ │ │ │ ├── modules/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── base.py │ │ │ │ │ ├── depthwise_sep_conv.py │ │ │ │ │ ├── fake_fakes.py │ │ │ │ │ ├── ffc.py │ │ │ │ │ ├── multidilated_conv.py │ │ │ │ │ ├── multiscale.py │ │ │ │ │ ├── pix2pixhd.py │ │ │ │ │ ├── spatial_transform.py │ │ │ │ │ └── squeeze_excitation.py │ │ │ │ ├── trainers/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── base.py │ │ │ │ │ └── default.py │ │ │ │ └── visualizers/ │ │ │ │ ├── __init__.py │ │ │ │ ├── base.py │ │ │ │ ├── colors.py │ │ │ │ ├── directory.py │ │ │ │ └── noop.py │ │ │ └── utils.py │ │ └── scripts/ │ │ ├── lama_config.yaml │ │ └── preprocessor_inpaint.py │ ├── forge_preprocessor_marigold/ │ │ ├── marigold/ │ │ │ ├── model/ │ │ │ │ ├── __init__.py │ │ │ │ ├── marigold_pipeline.py │ │ │ │ ├── rgb_encoder.py │ │ │ │ └── stacked_depth_AE.py │ │ │ └── util/ │ │ │ ├── batchsize.py │ │ │ ├── ensemble.py │ │ │ ├── image_util.py │ │ │ └── seed_all.py │ │ └── scripts/ │ │ └── preprocessor_marigold.py │ ├── forge_preprocessor_normalbae/ │ │ ├── annotator/ │ │ │ └── normalbae/ │ │ │ ├── LICENSE │ │ │ ├── __init__.py │ │ │ └── models/ │ │ │ ├── NNET.py │ │ │ ├── baseline.py │ │ │ └── submodules/ │ │ │ ├── decoder.py │ │ │ ├── efficientnet_repo/ │ │ │ │ ├── .gitignore │ │ │ │ ├── BENCHMARK.md │ │ │ │ ├── LICENSE │ │ │ │ ├── README.md │ │ │ │ ├── caffe2_benchmark.py │ │ │ │ ├── caffe2_validate.py │ │ │ │ ├── geffnet/ │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── activations/ │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ ├── activations.py │ │ │ │ │ │ ├── activations_jit.py │ │ │ │ │ │ └── activations_me.py │ │ │ │ │ ├── config.py │ │ │ │ │ ├── conv2d_layers.py │ │ │ │ │ ├── efficientnet_builder.py │ │ │ │ │ ├── gen_efficientnet.py │ │ │ │ │ ├── helpers.py │ │ │ │ │ ├── mobilenetv3.py │ │ │ │ │ ├── model_factory.py │ │ │ │ │ └── version.py │ │ │ │ ├── hubconf.py │ │ │ │ ├── onnx_export.py │ │ │ │ ├── onnx_optimize.py │ │ │ │ ├── onnx_to_caffe.py │ │ │ │ ├── onnx_validate.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── setup.py │ │ │ │ ├── utils.py │ │ │ │ └── validate.py │ │ │ ├── encoder.py │ │ │ └── submodules.py │ │ └── scripts/ │ │ └── preprocessor_normalbae.py │ ├── forge_preprocessor_recolor/ │ │ └── scripts/ │ │ └── preprocessor_recolor.py │ ├── forge_preprocessor_reference/ │ │ └── scripts/ │ │ └── forge_reference.py │ ├── forge_preprocessor_revision/ │ │ └── scripts/ │ │ └── preprocessor_revision.py │ ├── forge_preprocessor_tile/ │ │ └── scripts/ │ │ └── preprocessor_tile.py │ ├── forge_space_animagine_xl_31/ │ │ ├── forge_app.py │ │ └── space_meta.json │ ├── forge_space_birefnet/ │ │ ├── forge_app.py │ │ └── space_meta.json │ ├── forge_space_example/ │ │ ├── forge_app.py │ │ └── space_meta.json │ ├── forge_space_florence_2/ │ │ ├── forge_app.py │ │ └── space_meta.json │ ├── forge_space_geowizard/ │ │ ├── forge_app.py │ │ ├── geo_models/ │ │ │ ├── attention.py │ │ │ ├── geowizard_pipeline.py │ │ │ ├── transformer_2d.py │ │ │ ├── unet_2d_blocks.py │ │ │ └── unet_2d_condition.py │ │ ├── geo_utils/ │ │ │ ├── batch_size.py │ │ │ ├── colormap.py │ │ │ ├── common.py │ │ │ ├── dataset_configuration.py │ │ │ ├── de_normalized.py │ │ │ ├── depth2normal.py │ │ │ ├── depth_ensemble.py │ │ │ ├── image_util.py │ │ │ ├── normal_ensemble.py │ │ │ ├── seed_all.py │ │ │ └── surface_normal.py │ │ └── space_meta.json │ ├── forge_space_iclight/ │ │ ├── forge_app.py │ │ └── space_meta.json │ ├── forge_space_idm_vton/ │ │ ├── forge_app.py │ │ ├── requirements.txt │ │ ├── space_meta.json │ │ └── src/ │ │ ├── attentionhacked_garmnet.py │ │ ├── attentionhacked_tryon.py │ │ ├── transformerhacked_garmnet.py │ │ ├── transformerhacked_tryon.py │ │ ├── tryon_pipeline.py │ │ ├── unet_block_hacked_garmnet.py │ │ ├── unet_block_hacked_tryon.py │ │ ├── unet_hacked_garmnet.py │ │ └── unet_hacked_tryon.py │ ├── forge_space_illusion_diffusion/ │ │ ├── forge_app.py │ │ └── space_meta.json │ ├── forge_space_photo_maker_v2/ │ │ ├── forge_app.py │ │ └── space_meta.json │ ├── forge_space_sapiens_normal/ │ │ ├── forge_app.py │ │ └── space_meta.json │ ├── mobile/ │ │ └── javascript/ │ │ └── mobile.js │ ├── prompt-bracket-checker/ │ │ └── javascript/ │ │ └── prompt-bracket-checker.js │ ├── sd_forge_controlllite/ │ │ ├── lib_controllllite/ │ │ │ └── lib_controllllite.py │ │ └── scripts/ │ │ └── forge_controllllite.py │ ├── sd_forge_controlnet/ │ │ ├── .gitignore │ │ ├── LICENSE │ │ ├── install.py │ │ ├── javascript/ │ │ │ ├── active_units.js │ │ │ ├── canvas.js │ │ │ ├── modal.js │ │ │ ├── openpose_editor.js │ │ │ └── photopea.js │ │ ├── lib_controlnet/ │ │ │ ├── api.py │ │ │ ├── controlnet_ui/ │ │ │ │ ├── controlnet_ui_group.py │ │ │ │ ├── modal.py │ │ │ │ ├── openpose_editor.py │ │ │ │ └── photopea.py │ │ │ ├── enums.py │ │ │ ├── external_code.py │ │ │ ├── global_state.py │ │ │ ├── infotext.py │ │ │ ├── logging.py │ │ │ ├── lvminthin.py │ │ │ └── utils.py │ │ ├── preload.py │ │ ├── requirements.txt │ │ ├── scripts/ │ │ │ ├── controlnet.py │ │ │ └── xyz_grid_support.py │ │ └── style.css │ ├── sd_forge_dynamic_thresholding/ │ │ ├── LICENSE.txt │ │ ├── lib_dynamic_thresholding/ │ │ │ ├── dynthres.py │ │ │ └── dynthres_core.py │ │ └── scripts/ │ │ └── forge_dynamic_thresholding.py │ ├── sd_forge_fooocus_inpaint/ │ │ └── scripts/ │ │ ├── fooocus_inpaint_head │ │ └── forge_fooocus_inpaint.py │ ├── sd_forge_freeu/ │ │ └── scripts/ │ │ └── forge_freeu.py │ ├── sd_forge_ipadapter/ │ │ ├── LICENSE │ │ ├── lib_ipadapter/ │ │ │ ├── IPAdapterPlus.py │ │ │ └── resampler.py │ │ ├── scripts/ │ │ │ └── forge_ipadapter.py │ │ └── thanks │ ├── sd_forge_kohya_hrfix/ │ │ └── scripts/ │ │ └── kohya_hrfix.py │ ├── sd_forge_latent_modifier/ │ │ ├── LICENSE │ │ ├── README.md │ │ ├── lib_latent_modifier/ │ │ │ └── sampler_mega_modifier.py │ │ └── scripts/ │ │ └── forge_latent_modifier.py │ ├── sd_forge_lora/ │ │ ├── extra_networks_lora.py │ │ ├── lora.py │ │ ├── lora_logger.py │ │ ├── network.py │ │ ├── networks.py │ │ ├── preload.py │ │ ├── scripts/ │ │ │ └── lora_script.py │ │ ├── ui_edit_user_metadata.py │ │ └── ui_extra_networks_lora.py │ ├── sd_forge_multidiffusion/ │ │ ├── lib_multidiffusion/ │ │ │ └── tiled_diffusion.py │ │ └── scripts/ │ │ └── forge_multidiffusion.py │ ├── sd_forge_neveroom/ │ │ └── scripts/ │ │ └── forge_never_oom.py │ ├── sd_forge_perturbed_attention/ │ │ └── scripts/ │ │ └── forge_perturbed_attention.py │ ├── sd_forge_sag/ │ │ └── scripts/ │ │ └── forge_sag.py │ ├── sd_forge_stylealign/ │ │ └── scripts/ │ │ └── forge_stylealign.py │ └── soft-inpainting/ │ └── scripts/ │ └── soft_inpainting.py ├── html/ │ ├── extra-networks-card.html │ ├── extra-networks-copy-path-button.html │ ├── extra-networks-edit-item-button.html │ ├── extra-networks-metadata-button.html │ ├── extra-networks-no-cards.html │ ├── extra-networks-pane-dirs.html │ ├── extra-networks-pane-tree.html │ ├── extra-networks-pane.html │ ├── extra-networks-tree-button.html │ ├── footer.html │ └── licenses.html ├── javascript/ │ ├── aspectRatioOverlay.js │ ├── contextMenus.js │ ├── dragdrop.js │ ├── edit-attention.js │ ├── edit-order.js │ ├── extensions.js │ ├── extraNetworks.js │ ├── generationParams.js │ ├── gradio.js │ ├── hints.js │ ├── hires_fix.js │ ├── imageMaskFix.js │ ├── imageviewer.js │ ├── imageviewerGamepad.js │ ├── inputAccordion.js │ ├── localStorage.js │ ├── localization.js │ ├── notification.js │ ├── profilerVisualization.js │ ├── progressbar.js │ ├── resizeHandle.js │ ├── settings.js │ ├── textualInversion.js │ ├── token-counters.js │ ├── ui.js │ └── ui_settings_hints.js ├── k_diffusion/ │ ├── deis.py │ ├── external.py │ ├── sampling.py │ └── utils.py ├── launch.py ├── localizations/ │ └── Put localization files here.txt ├── modules/ │ ├── api/ │ │ ├── api.py │ │ └── models.py │ ├── cache.py │ ├── call_queue.py │ ├── cmd_args.py │ ├── codeformer_model.py │ ├── config_states.py │ ├── dat_model.py │ ├── deepbooru.py │ ├── deepbooru_model.py │ ├── devices.py │ ├── errors.py │ ├── esrgan_model.py │ ├── extensions.py │ ├── extra_networks.py │ ├── extra_networks_hypernet.py │ ├── extras.py │ ├── face_restoration.py │ ├── face_restoration_utils.py │ ├── fifo_lock.py │ ├── gfpgan_model.py │ ├── gitpython_hack.py │ ├── gradio_extensions.py │ ├── hashes.py │ ├── hat_model.py │ ├── hypernetworks/ │ │ ├── hypernetwork.py │ │ └── ui.py │ ├── images.py │ ├── img2img.py │ ├── import_hook.py │ ├── infotext_utils.py │ ├── infotext_versions.py │ ├── initialize.py │ ├── initialize_util.py │ ├── interrogate.py │ ├── launch_utils.py │ ├── localization.py │ ├── logging_config.py │ ├── lowvram.py │ ├── mac_specific.py │ ├── masking.py │ ├── memmon.py │ ├── modelloader.py │ ├── models/ │ │ ├── diffusion/ │ │ │ ├── ddpm_edit.py │ │ │ └── uni_pc/ │ │ │ ├── __init__.py │ │ │ ├── sampler.py │ │ │ └── uni_pc.py │ │ └── sd3/ │ │ ├── mmdit.py │ │ ├── other_impls.py │ │ ├── sd3_cond.py │ │ ├── sd3_impls.py │ │ └── sd3_model.py │ ├── ngrok.py │ ├── npu_specific.py │ ├── options.py │ ├── patches.py │ ├── paths.py │ ├── paths_internal.py │ ├── postprocessing.py │ ├── processing.py │ ├── processing_scripts/ │ │ ├── comments.py │ │ ├── refiner.py │ │ ├── sampler.py │ │ └── seed.py │ ├── profiling.py │ ├── progress.py │ ├── prompt_parser.py │ ├── realesrgan_model.py │ ├── restart.py │ ├── rng.py │ ├── rng_philox.py │ ├── safe.py │ ├── script_callbacks.py │ ├── script_loading.py │ ├── scripts.py │ ├── scripts_auto_postprocessing.py │ ├── scripts_postprocessing.py │ ├── sd_disable_initialization.py │ ├── sd_emphasis.py │ ├── sd_hijack.py │ ├── sd_hijack_checkpoint.py │ ├── sd_hijack_clip.py │ ├── sd_hijack_clip_old.py │ ├── sd_hijack_ip2p.py │ ├── sd_hijack_open_clip.py │ ├── sd_hijack_optimizations.py │ ├── sd_hijack_unet.py │ ├── sd_hijack_utils.py │ ├── sd_hijack_xlmr.py │ ├── sd_models.py │ ├── sd_models_config.py │ ├── sd_models_types.py │ ├── sd_models_xl.py │ ├── sd_samplers.py │ ├── sd_samplers_cfg_denoiser.py │ ├── sd_samplers_common.py │ ├── sd_samplers_compvis.py │ ├── sd_samplers_extra.py │ ├── sd_samplers_kdiffusion.py │ ├── sd_samplers_lcm.py │ ├── sd_samplers_timesteps.py │ ├── sd_samplers_timesteps_impl.py │ ├── sd_schedulers.py │ ├── sd_unet.py │ ├── sd_vae.py │ ├── sd_vae_approx.py │ ├── sd_vae_taesd.py │ ├── shared.py │ ├── shared_cmd_options.py │ ├── shared_gradio_themes.py │ ├── shared_init.py │ ├── shared_items.py │ ├── shared_options.py │ ├── shared_state.py │ ├── shared_total_tqdm.py │ ├── stealth_infotext.py │ ├── styles.py │ ├── sysinfo.py │ ├── textual_inversion/ │ │ ├── autocrop.py │ │ ├── image_embedding.py │ │ ├── textual_inversion.py │ │ └── ui.py │ ├── timer.py │ ├── torch_utils.py │ ├── txt2img.py │ ├── ui.py │ ├── ui_checkpoint_merger.py │ ├── ui_common.py │ ├── ui_components.py │ ├── ui_extensions.py │ ├── ui_extra_networks.py │ ├── ui_extra_networks_checkpoints.py │ ├── ui_extra_networks_checkpoints_user_metadata.py │ ├── ui_extra_networks_hypernets.py │ ├── ui_extra_networks_textual_inversion.py │ ├── ui_extra_networks_user_metadata.py │ ├── ui_gradio_extensions.py │ ├── ui_loadsave.py │ ├── ui_postprocessing.py │ ├── ui_prompt_styles.py │ ├── ui_settings.py │ ├── ui_tempdir.py │ ├── ui_toprow.py │ ├── upscaler.py │ ├── upscaler_utils.py │ ├── util.py │ ├── xlmr.py │ ├── xlmr_m18.py │ └── xpu_specific.py ├── modules_forge/ │ ├── alter_samplers.py │ ├── bnb_installer.py │ ├── config.py │ ├── cuda_malloc.py │ ├── diffusers_patcher.py │ ├── forge_canvas/ │ │ ├── canvas.css │ │ ├── canvas.html │ │ └── canvas.py │ ├── forge_space.py │ ├── forge_version.py │ ├── gradio_compile.py │ ├── initialization.py │ ├── main_entry.py │ ├── main_thread.py │ ├── patch_basic.py │ ├── shared.py │ ├── shared_options.py │ ├── supported_controlnet.py │ ├── supported_preprocessor.py │ └── utils.py ├── package.json ├── packages_3rdparty/ │ ├── README.md │ ├── comfyui_lora_collection/ │ │ ├── LICENSE │ │ ├── lora.py │ │ └── utils.py │ ├── gguf/ │ │ ├── LICENSE │ │ ├── README.md │ │ ├── __init__.py │ │ ├── constants.py │ │ ├── gguf_reader.py │ │ ├── gguf_writer.py │ │ ├── lazy.py │ │ ├── metadata.py │ │ ├── quants.py │ │ ├── quick_4bits_ops.py │ │ ├── tensor_mapping.py │ │ ├── utility.py │ │ └── vocab.py │ └── webui_lora_collection/ │ ├── LICENSE.txt │ ├── lora.py │ ├── lyco_helpers.py │ ├── network.py │ ├── network_full.py │ ├── network_glora.py │ ├── network_hada.py │ ├── network_ia3.py │ ├── network_lokr.py │ ├── network_lora.py │ ├── network_norm.py │ └── network_oft.py ├── pyproject.toml ├── requirements_versions.txt ├── script.js ├── scripts/ │ ├── custom_code.py │ ├── img2imgalt.py │ ├── loopback.py │ ├── outpainting_mk_2.py │ ├── poor_mans_outpainting.py │ ├── postprocessing_codeformer.py │ ├── postprocessing_focal_crop.py │ ├── postprocessing_gfpgan.py │ ├── postprocessing_upscale.py │ ├── prompt_matrix.py │ ├── prompts_from_file.py │ ├── sd_upscale.py │ └── xyz_grid.py ├── spaces.py ├── style.css ├── styles_integrated.csv ├── webui-macos-env.sh ├── webui.bat ├── webui.py └── webui.sh
SYMBOL INDEX (82 symbols across 8 files)
FILE: backend/attention.py
function get_attn_precision (line 25) | def get_attn_precision(attn_precision=torch.float32):
function exists (line 33) | def exists(val):
function attention_basic (line 37) | def attention_basic(q, k, v, heads, mask=None, attn_precision=None, skip...
function attention_sub_quad (line 96) | def attention_sub_quad(query, key, value, heads, mask=None, attn_precisi...
function attention_split (line 167) | def attention_split(q, k, v, heads, mask=None, attn_precision=None, skip...
function attention_xformers (line 280) | def attention_xformers(q, k, v, heads, mask=None, attn_precision=None, s...
function attention_pytorch (line 324) | def attention_pytorch(q, k, v, heads, mask=None, attn_precision=None, sk...
function slice_attention_single_head_spatial (line 342) | def slice_attention_single_head_spatial(q, k, v):
function normal_attention_single_head_spatial (line 380) | def normal_attention_single_head_spatial(q, k, v):
function xformers_attention_single_head_spatial (line 395) | def xformers_attention_single_head_spatial(q, k, v):
function pytorch_attention_single_head_spatial (line 412) | def pytorch_attention_single_head_spatial(q, k, v):
class AttentionProcessorForge (line 454) | class AttentionProcessorForge:
method __call__ (line 455) | def __call__(self, attn, hidden_states, encoder_hidden_states, attenti...
FILE: backend/diffusion_engine/base.py
class ForgeObjects (line 7) | class ForgeObjects:
method __init__ (line 8) | def __init__(self, unet, clip, vae, clipvision):
method shallow_copy (line 14) | def shallow_copy(self):
class ForgeDiffusionEngine (line 23) | class ForgeDiffusionEngine:
method __init__ (line 26) | def __init__(self, estimated_config, huggingface_components):
method set_clip_skip (line 38) | def set_clip_skip(self, clip_skip):
method get_first_stage_encoding (line 41) | def get_first_stage_encoding(self, x):
method get_learned_conditioning (line 44) | def get_learned_conditioning(self, prompt: list[str]):
method encode_first_stage (line 47) | def encode_first_stage(self, x):
method decode_first_stage (line 50) | def decode_first_stage(self, x):
method get_prompt_lengths_on_ui (line 53) | def get_prompt_lengths_on_ui(self, prompt):
method is_webui_legacy_model (line 56) | def is_webui_legacy_model(self):
method fix_for_webui_backward_compatibility (line 59) | def fix_for_webui_backward_compatibility(self):
method save_unet (line 70) | def save_unet(self, filename):
method save_checkpoint (line 75) | def save_checkpoint(self, filename):
FILE: backend/diffusion_engine/chroma.py
class Chroma (line 13) | class Chroma(ForgeDiffusionEngine):
method __init__ (line 14) | def __init__(self, estimated_config, huggingface_components):
method set_clip_skip (line 49) | def set_clip_skip(self, clip_skip):
method get_learned_conditioning (line 53) | def get_learned_conditioning(self, prompt: list[str]):
method get_prompt_lengths_on_ui (line 58) | def get_prompt_lengths_on_ui(self, prompt):
method encode_first_stage (line 63) | def encode_first_stage(self, x):
method decode_first_stage (line 69) | def decode_first_stage(self, x):
FILE: backend/diffusion_engine/flux.py
class Flux (line 15) | class Flux(ForgeDiffusionEngine):
method __init__ (line 18) | def __init__(self, estimated_config, huggingface_components):
method set_clip_skip (line 80) | def set_clip_skip(self, clip_skip):
method get_learned_conditioning (line 84) | def get_learned_conditioning(self, prompt: list[str]):
method get_prompt_lengths_on_ui (line 100) | def get_prompt_lengths_on_ui(self, prompt):
method encode_first_stage (line 105) | def encode_first_stage(self, x):
method decode_first_stage (line 111) | def decode_first_stage(self, x):
FILE: backend/diffusion_engine/sd15.py
class StableDiffusion (line 16) | class StableDiffusion(ForgeDiffusionEngine):
method __init__ (line 19) | def __init__(self, estimated_config, huggingface_components):
method set_clip_skip (line 60) | def set_clip_skip(self, clip_skip):
method get_learned_conditioning (line 64) | def get_learned_conditioning(self, prompt: list[str]):
method get_prompt_lengths_on_ui (line 70) | def get_prompt_lengths_on_ui(self, prompt):
method encode_first_stage (line 75) | def encode_first_stage(self, x):
method decode_first_stage (line 81) | def decode_first_stage(self, x):
method save_checkpoint (line 86) | def save_checkpoint(self, filename):
FILE: backend/diffusion_engine/sd20.py
class StableDiffusion2 (line 16) | class StableDiffusion2(ForgeDiffusionEngine):
method __init__ (line 19) | def __init__(self, estimated_config, huggingface_components):
method set_clip_skip (line 60) | def set_clip_skip(self, clip_skip):
method get_learned_conditioning (line 64) | def get_learned_conditioning(self, prompt: list[str]):
method get_prompt_lengths_on_ui (line 70) | def get_prompt_lengths_on_ui(self, prompt):
method encode_first_stage (line 75) | def encode_first_stage(self, x):
method decode_first_stage (line 81) | def decode_first_stage(self, x):
method save_checkpoint (line 86) | def save_checkpoint(self, filename):
FILE: backend/diffusion_engine/sd35.py
function SD3_clip_target (line 18) | def SD3_clip_target(self, state_dict={}):
class StableDiffusion3 (line 25) | class StableDiffusion3(ForgeDiffusionEngine):
method __init__ (line 28) | def __init__(self, estimated_config, huggingface_components):
method set_clip_skip (line 97) | def set_clip_skip(self, clip_skip):
method get_learned_conditioning (line 102) | def get_learned_conditioning(self, prompt: list[str]):
method get_prompt_lengths_on_ui (line 134) | def get_prompt_lengths_on_ui(self, prompt):
method encode_first_stage (line 139) | def encode_first_stage(self, x):
method decode_first_stage (line 145) | def decode_first_stage(self, x):
FILE: backend/diffusion_engine/sdxl.py
class StableDiffusionXL (line 19) | class StableDiffusionXL(ForgeDiffusionEngine):
method __init__ (line 22) | def __init__(self, estimated_config, huggingface_components):
method set_clip_skip (line 81) | def set_clip_skip(self, clip_skip):
method get_learned_conditioning (line 86) | def get_learned_conditioning(self, prompt: list[str]):
method get_prompt_lengths_on_ui (line 124) | def get_prompt_lengths_on_ui(self, prompt):
method encode_first_stage (line 129) | def encode_first_stage(self, x):
method decode_first_stage (line 135) | def decode_first_stage(self, x):
method save_checkpoint (line 140) | def save_checkpoint(self, filename):
class StableDiffusionXLRefiner (line 157) | class StableDiffusionXLRefiner(ForgeDiffusionEngine):
method __init__ (line 160) | def __init__(self, estimated_config, huggingface_components):
method set_clip_skip (line 203) | def set_clip_skip(self, clip_skip):
method get_learned_conditioning (line 207) | def get_learned_conditioning(self, prompt: list[str]):
method get_prompt_lengths_on_ui (line 242) | def get_prompt_lengths_on_ui(self, prompt):
method encode_first_stage (line 247) | def encode_first_stage(self, x):
method decode_first_stage (line 253) | def decode_first_stage(self, x):
method save_checkpoint (line 258) | def save_checkpoint(self, filename):
Copy disabled (too large)
Download .json
Condensed preview — 1490 files, each showing path, character count, and a content snippet. Download the .json file for the full structured content (17,562K chars).
[
{
"path": ".eslintignore",
"chars": 87,
"preview": "extensions\nextensions-disabled\nextensions-builtin/sd_forge_controlnet\nrepositories\nvenv"
},
{
"path": ".eslintrc.js",
"chars": 3423,
"preview": "/* global module */\nmodule.exports = {\n env: {\n browser: true,\n es2021: true,\n },\n extends: \"esli"
},
{
"path": ".git-blame-ignore-revs",
"chars": 55,
"preview": "# Apply ESlint\n9c54b78d9dde5601e916f308d9a9d6953ec39430"
},
{
"path": ".gitignore",
"chars": 734,
"preview": "huggingface_space_mirror/\nrandom_test.py\n__pycache__\n*.ckpt\n*.safetensors\n*.pth\n*.dev.js\n*_s.py\n*_u.py\n*_m.py\n*_i.py\n.DS"
},
{
"path": ".pylintrc",
"chars": 119,
"preview": "# See https://pylint.pycqa.org/en/latest/user_guide/messages/message_control.html\n[MESSAGES CONTROL]\ndisable=C,R,W,E,I\n"
},
{
"path": "CHANGELOG.md",
"chars": 97076,
"preview": "## 1.10.1\r\n\r\n### Bug Fixes:\r\n* fix image upscale on cpu ([#16275](https://github.com/AUTOMATIC1111/stable-diffusion-webu"
},
{
"path": "CITATION.cff",
"chars": 243,
"preview": "cff-version: 1.2.0\nmessage: \"If you use this software, please cite it as below.\"\nauthors:\n - given-names: AUTOMATIC1111"
},
{
"path": "CODEOWNERS",
"chars": 21,
"preview": "* @lllyasviel\r\n"
},
{
"path": "LICENSE.txt",
"chars": 36431,
"preview": " GNU AFFERO GENERAL PUBLIC LICENSE\r\n Version 3, 19 November 2007\r\n\r\n "
},
{
"path": "NEWS.md",
"chars": 1099,
"preview": "About Gradio 5: will try to upgrade to Gradio 5 at about 2025 March. If failed, then will try again on about 2025 June. "
},
{
"path": "README.md",
"chars": 12192,
"preview": "# Stable Diffusion WebUI Forge\n\nStable Diffusion WebUI Forge is a platform on top of [Stable Diffusion WebUI](https://gi"
},
{
"path": "_typos.toml",
"chars": 146,
"preview": "[default.extend-words]\n# Part of \"RGBa\" (Pillow's pre-multiplied alpha RGB mode)\nBa = \"Ba\"\n# HSA is something AMD uses f"
},
{
"path": "backend/README.md",
"chars": 24,
"preview": "# WIP Backend for Forge\n"
},
{
"path": "backend/args.py",
"chars": 2932,
"preview": "import argparse\n\nparser = argparse.ArgumentParser()\n\nparser.add_argument(\"--gpu-device-id\", type=int, default=None, meta"
},
{
"path": "backend/attention.py",
"chars": 16839,
"preview": "import math\nimport torch\nimport einops\n\nfrom backend.args import args\nfrom backend import memory_management\nfrom backend"
},
{
"path": "backend/diffusion_engine/base.py",
"chars": 2442,
"preview": "import torch\nimport safetensors.torch as sf\n\nfrom backend import utils\n\n\nclass ForgeObjects:\n def __init__(self, unet"
},
{
"path": "backend/diffusion_engine/chroma.py",
"chars": 2726,
"preview": "import torch\n\nfrom huggingface_guess import model_list\nfrom backend.diffusion_engine.base import ForgeDiffusionEngine, F"
},
{
"path": "backend/diffusion_engine/flux.py",
"chars": 4407,
"preview": "import torch\n\nfrom huggingface_guess import model_list\nfrom backend.diffusion_engine.base import ForgeDiffusionEngine, F"
},
{
"path": "backend/diffusion_engine/sd15.py",
"chars": 3729,
"preview": "import torch\n\nfrom huggingface_guess import model_list\nfrom backend.diffusion_engine.base import ForgeDiffusionEngine, F"
},
{
"path": "backend/diffusion_engine/sd20.py",
"chars": 3731,
"preview": "import torch\n\nfrom huggingface_guess import model_list\nfrom backend.diffusion_engine.base import ForgeDiffusionEngine, F"
},
{
"path": "backend/diffusion_engine/sd35.py",
"chars": 5801,
"preview": "import torch\r\n\r\nfrom huggingface_guess import model_list\r\nfrom backend.diffusion_engine.base import ForgeDiffusionEngine"
},
{
"path": "backend/diffusion_engine/sdxl.py",
"chars": 10278,
"preview": "import torch\n\nfrom huggingface_guess import model_list\nfrom backend.diffusion_engine.base import ForgeDiffusionEngine, F"
},
{
"path": "backend/huggingface/Chroma/model_index.json",
"chars": 407,
"preview": "{\n \"_class_name\": \"FluxPipeline\",\n \"_diffusers_version\": \"0.30.0.dev0\",\n \"scheduler\": [\n \"diffusers\",\n \"FlowMat"
},
{
"path": "backend/huggingface/Chroma/scheduler/scheduler_config.json",
"chars": 274,
"preview": "{\n \"_class_name\": \"FlowMatchEulerDiscreteScheduler\",\n \"_diffusers_version\": \"0.30.0.dev0\",\n \"base_image_seq_len\": 256"
},
{
"path": "backend/huggingface/Chroma/text_encoder/config.json",
"chars": 509,
"preview": "{\n \"d_ff\": 10240,\n \"d_kv\": 64,\n \"d_model\": 4096,\n \"decoder_start_token_id\": 0,\n \"dropout_rate\": 0.1,\n \"eos_token_i"
},
{
"path": "backend/huggingface/Chroma/text_encoder/model.safetensors.index.json",
"chars": 19885,
"preview": "{\n \"metadata\": {\n \"total_size\": 9524621312\n },\n \"weight_map\": {\n \"encoder.block.0.layer.0.SelfAttention.k.weigh"
},
{
"path": "backend/huggingface/Chroma/tokenizer/special_tokens_map.json",
"chars": 2543,
"preview": "{\n \"additional_special_tokens\": [\n \"<extra_id_0>\",\n \"<extra_id_1>\",\n \"<extra_id_2>\",\n \"<extra_id_3>\",\n \""
},
{
"path": "backend/huggingface/Chroma/tokenizer/tokenizer.json",
"chars": 2377487,
"preview": "{\n \"version\": \"1.0\",\n \"truncation\": null,\n \"padding\": null,\n \"added_tokens\": [\n {\n \"id\": 0,\n \"content\":"
},
{
"path": "backend/huggingface/Chroma/tokenizer/tokenizer_config.json",
"chars": 20790,
"preview": "{\n \"added_tokens_decoder\": {\n \"0\": {\n \"content\": \"<pad>\",\n \"lstrip\": false,\n \"normalized\": false,\n "
},
{
"path": "backend/huggingface/Chroma/vae/config.json",
"chars": 820,
"preview": "{\n \"_class_name\": \"AutoencoderKL\",\n \"_diffusers_version\": \"0.30.0.dev0\",\n \"_name_or_path\": \"../checkpoints/flux-dev\","
},
{
"path": "backend/huggingface/Kwai-Kolors/Kolors/model_index.json",
"chars": 427,
"preview": "{\n \"_class_name\": \"StableDiffusionXLPipeline\",\n \"_diffusers_version\": \"0.18.0.dev0\",\n \"force_zeros_for_empty_prompt\":"
},
{
"path": "backend/huggingface/Kwai-Kolors/Kolors/scheduler/scheduler_config.json",
"chars": 606,
"preview": "{\n \"_class_name\": \"EulerDiscreteScheduler\",\n \"_diffusers_version\": \"0.18.0.dev0\",\n \"beta_schedule\": \"scaled_linear\",\n"
},
{
"path": "backend/huggingface/Kwai-Kolors/Kolors/text_encoder/config.json",
"chars": 1323,
"preview": "{\n \"_name_or_path\": \"THUDM/chatglm3-6b-base\",\n \"model_type\": \"chatglm\",\n \"architectures\": [\n \"ChatGLMModel\"\n ],\n "
},
{
"path": "backend/huggingface/Kwai-Kolors/Kolors/text_encoder/pytorch_model.bin.index.json",
"chars": 20437,
"preview": "{\n \"metadata\": {\n \"total_size\": 12487168064\n },\n \"weight_map\": {\n \"transformer.embedding.word_embeddings.weight"
},
{
"path": "backend/huggingface/Kwai-Kolors/Kolors/text_encoder/tokenizer_config.json",
"chars": 249,
"preview": "{\n \"name_or_path\": \"THUDM/chatglm3-6b-base\",\n \"remove_space\": false,\n \"do_lower_case\": false,\n \"tokenizer_class\": \"C"
},
{
"path": "backend/huggingface/Kwai-Kolors/Kolors/tokenizer/tokenizer_config.json",
"chars": 249,
"preview": "{\n \"name_or_path\": \"THUDM/chatglm3-6b-base\",\n \"remove_space\": false,\n \"do_lower_case\": false,\n \"tokenizer_class\": \"C"
},
{
"path": "backend/huggingface/Kwai-Kolors/Kolors/unet/config.json",
"chars": 1785,
"preview": "{\n \"_class_name\": \"UNet2DConditionModel\",\n \"_diffusers_version\": \"0.27.0.dev0\",\n \"act_fn\": \"silu\",\n \"addition_embed_"
},
{
"path": "backend/huggingface/Kwai-Kolors/Kolors/vae/config.json",
"chars": 611,
"preview": "{\n \"_class_name\": \"AutoencoderKL\",\n \"_diffusers_version\": \"0.18.0.dev0\",\n \"_name_or_path\": \"./vae\",\n \"act_fn\": \"silu"
},
{
"path": "backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/model_index.json",
"chars": 641,
"preview": "{\n \"_class_name\": \"HunyuanDiTPipeline\",\n \"_diffusers_version\": \"0.29.0.dev0\",\n \"feature_extractor\": [\n null,\n n"
},
{
"path": "backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/scheduler/scheduler_config.json",
"chars": 571,
"preview": "{\n \"_class_name\": \"DDPMScheduler\",\n \"_diffusers_version\": \"0.29.0.dev0\",\n \"beta_end\": 0.03,\n \"beta_schedule\": \"scale"
},
{
"path": "backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/text_encoder/config.json",
"chars": 840,
"preview": "{\n \"architectures\": [\n \"BertModel\"\n ],\n \"attention_probs_dropout_prob\": 0.1,\n \"bos_token_id\": 0,\n \"classifier_dr"
},
{
"path": "backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/text_encoder_2/config.json",
"chars": 776,
"preview": "{\n \"architectures\": [\n \"T5EncoderModel\"\n ],\n \"classifier_dropout\": 0.0,\n \"d_ff\": 5120,\n \"d_kv\": 64,\n \"d_model\":"
},
{
"path": "backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/text_encoder_2/model.safetensors.index.json",
"chars": 19885,
"preview": "{\n \"metadata\": {\n \"total_size\": 6679834624\n },\n \"weight_map\": {\n \"encoder.block.0.layer.0.SelfAttention.k.weigh"
},
{
"path": "backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer/special_tokens_map.json",
"chars": 695,
"preview": "{\n \"cls_token\": {\n \"content\": \"[CLS]\",\n \"lstrip\": false,\n \"normalized\": false,\n \"rstrip\": false,\n \"singl"
},
{
"path": "backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer/tokenizer_config.json",
"chars": 1241,
"preview": "{\n \"added_tokens_decoder\": {\n \"0\": {\n \"content\": \"[PAD]\",\n \"lstrip\": false,\n \"normalized\": false,\n "
},
{
"path": "backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer/vocab.txt",
"chars": 281526,
"preview": "[PAD]\n[unused1]\n[unused2]\n[unused3]\n[unused4]\n[unused5]\n[unused6]\n[unused7]\n[unused8]\n[unused9]\n[unused10]\n[unused11]\n[u"
},
{
"path": "backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer_2/special_tokens_map.json",
"chars": 416,
"preview": "{\n \"eos_token\": {\n \"content\": \"</s>\",\n \"lstrip\": false,\n \"normalized\": false,\n \"rstrip\": false,\n \"single"
},
{
"path": "backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer_2/tokenizer_config.json",
"chars": 861,
"preview": "{\n \"add_prefix_space\": true,\n \"added_tokens_decoder\": {\n \"0\": {\n \"content\": \"<pad>\",\n \"lstrip\": false,\n "
},
{
"path": "backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/transformer/config.json",
"chars": 493,
"preview": "{\n \"_class_name\": \"HunyuanDiT2DModel\",\n \"_diffusers_version\": \"0.29.0.dev0\",\n \"activation_fn\": \"gelu-approximate\",\n "
},
{
"path": "backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/vae/config.json",
"chars": 654,
"preview": "{\n \"_class_name\": \"AutoencoderKL\",\n \"_diffusers_version\": \"0.29.0.dev0\",\n \"act_fn\": \"silu\",\n \"block_out_channels\": ["
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/model_index.json",
"chars": 536,
"preview": "{\n \"_class_name\": \"FluxPipeline\",\n \"_diffusers_version\": \"0.30.0.dev0\",\n \"scheduler\": [\n \"diffusers\",\n \"FlowMat"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/scheduler/scheduler_config.json",
"chars": 273,
"preview": "{\n \"_class_name\": \"FlowMatchEulerDiscreteScheduler\",\n \"_diffusers_version\": \"0.30.0.dev0\",\n \"base_image_seq_len\": 256"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/text_encoder/config.json",
"chars": 613,
"preview": "{\n \"_name_or_path\": \"openai/clip-vit-large-patch14\",\n \"architectures\": [\n \"CLIPTextModel\"\n ],\n \"attention_dropout"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/text_encoder_2/config.json",
"chars": 509,
"preview": "{\n \"d_ff\": 10240,\n \"d_kv\": 64,\n \"d_model\": 4096,\n \"decoder_start_token_id\": 0,\n \"dropout_rate\": 0.1,\n \"eos_token_i"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/text_encoder_2/model.safetensors.index.json",
"chars": 19885,
"preview": "{\n \"metadata\": {\n \"total_size\": 9524621312\n },\n \"weight_map\": {\n \"encoder.block.0.layer.0.SelfAttention.k.weigh"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer/merges.txt",
"chars": 515308,
"preview": "#version: 0.2\ni n\nt h\na n\nr e\na r\ne r\nth e</w>\nin g</w>\no u\no n\ns t\no r\ne n\no n</w>\na l\na t\ne r</w>\ni t\ni n</w>\nt o</w>\n"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer/special_tokens_map.json",
"chars": 588,
"preview": "{\n \"bos_token\": {\n \"content\": \"<|startoftext|>\",\n \"lstrip\": false,\n \"normalized\": true,\n \"rstrip\": false,\n "
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer/tokenizer_config.json",
"chars": 705,
"preview": "{\n \"add_prefix_space\": false,\n \"added_tokens_decoder\": {\n \"49406\": {\n \"content\": \"<|startoftext|>\",\n \"lst"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer/vocab.json",
"chars": 1050327,
"preview": "{\n \"!\": 0,\n \"!!\": 1443,\n \"!!!\": 11194,\n \"!!!!\": 4003,\n \"!!!!!!!!\": 11281,\n \"!!!!!!!!!!!!!!!!\": 30146,\n \"!!!!!!!!!"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer_2/special_tokens_map.json",
"chars": 2543,
"preview": "{\n \"additional_special_tokens\": [\n \"<extra_id_0>\",\n \"<extra_id_1>\",\n \"<extra_id_2>\",\n \"<extra_id_3>\",\n \""
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer_2/tokenizer.json",
"chars": 2377487,
"preview": "{\n \"version\": \"1.0\",\n \"truncation\": null,\n \"padding\": null,\n \"added_tokens\": [\n {\n \"id\": 0,\n \"content\":"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer_2/tokenizer_config.json",
"chars": 20790,
"preview": "{\n \"added_tokens_decoder\": {\n \"0\": {\n \"content\": \"<pad>\",\n \"lstrip\": false,\n \"normalized\": false,\n "
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/transformer/config.json",
"chars": 378,
"preview": "{\n \"_class_name\": \"FluxTransformer2DModel\",\n \"_diffusers_version\": \"0.30.0.dev0\",\n \"_name_or_path\": \"../checkpoints/f"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/transformer/diffusion_pytorch_model.safetensors.index.json",
"chars": 121262,
"preview": "{\n \"metadata\": {\n \"total_size\": 23802816640\n },\n \"weight_map\": {\n \"context_embedder.bias\": \"diffusion_pytorch_m"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-dev/vae/config.json",
"chars": 820,
"preview": "{\n \"_class_name\": \"AutoencoderKL\",\n \"_diffusers_version\": \"0.30.0.dev0\",\n \"_name_or_path\": \"../checkpoints/flux-dev\","
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/model_index.json",
"chars": 536,
"preview": "{\n \"_class_name\": \"FluxPipeline\",\n \"_diffusers_version\": \"0.30.0.dev0\",\n \"scheduler\": [\n \"diffusers\",\n \"FlowMat"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/scheduler/scheduler_config.json",
"chars": 274,
"preview": "{\n \"_class_name\": \"FlowMatchEulerDiscreteScheduler\",\n \"_diffusers_version\": \"0.30.0.dev0\",\n \"base_image_seq_len\": 256"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/text_encoder/config.json",
"chars": 613,
"preview": "{\n \"_name_or_path\": \"openai/clip-vit-large-patch14\",\n \"architectures\": [\n \"CLIPTextModel\"\n ],\n \"attention_dropout"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/text_encoder_2/config.json",
"chars": 509,
"preview": "{\n \"d_ff\": 10240,\n \"d_kv\": 64,\n \"d_model\": 4096,\n \"decoder_start_token_id\": 0,\n \"dropout_rate\": 0.1,\n \"eos_token_i"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/text_encoder_2/model.safetensors.index.json",
"chars": 19885,
"preview": "{\n \"metadata\": {\n \"total_size\": 9524621312\n },\n \"weight_map\": {\n \"encoder.block.0.layer.0.SelfAttention.k.weigh"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer/merges.txt",
"chars": 515308,
"preview": "#version: 0.2\ni n\nt h\na n\nr e\na r\ne r\nth e</w>\nin g</w>\no u\no n\ns t\no r\ne n\no n</w>\na l\na t\ne r</w>\ni t\ni n</w>\nt o</w>\n"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer/special_tokens_map.json",
"chars": 588,
"preview": "{\n \"bos_token\": {\n \"content\": \"<|startoftext|>\",\n \"lstrip\": false,\n \"normalized\": true,\n \"rstrip\": false,\n "
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer/tokenizer_config.json",
"chars": 705,
"preview": "{\n \"add_prefix_space\": false,\n \"added_tokens_decoder\": {\n \"49406\": {\n \"content\": \"<|startoftext|>\",\n \"lst"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer/vocab.json",
"chars": 1050327,
"preview": "{\n \"!\": 0,\n \"!!\": 1443,\n \"!!!\": 11194,\n \"!!!!\": 4003,\n \"!!!!!!!!\": 11281,\n \"!!!!!!!!!!!!!!!!\": 30146,\n \"!!!!!!!!!"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer_2/special_tokens_map.json",
"chars": 2543,
"preview": "{\n \"additional_special_tokens\": [\n \"<extra_id_0>\",\n \"<extra_id_1>\",\n \"<extra_id_2>\",\n \"<extra_id_3>\",\n \""
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer_2/tokenizer.json",
"chars": 2377487,
"preview": "{\n \"version\": \"1.0\",\n \"truncation\": null,\n \"padding\": null,\n \"added_tokens\": [\n {\n \"id\": 0,\n \"content\":"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer_2/tokenizer_config.json",
"chars": 20790,
"preview": "{\n \"added_tokens_decoder\": {\n \"0\": {\n \"content\": \"<pad>\",\n \"lstrip\": false,\n \"normalized\": false,\n "
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/transformer/config.json",
"chars": 321,
"preview": "{\n \"_class_name\": \"FluxTransformer2DModel\",\n \"_diffusers_version\": \"0.30.0.dev0\",\n \"attention_head_dim\": 128,\n \"guid"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/transformer/diffusion_pytorch_model.safetensors.index.json",
"chars": 120822,
"preview": "{\n \"metadata\": {\n \"total_size\": 23782357120\n },\n \"weight_map\": {\n \"context_embedder.bias\": \"diffusion_pytorch_m"
},
{
"path": "backend/huggingface/black-forest-labs/FLUX.1-schnell/vae/config.json",
"chars": 820,
"preview": "{\n \"_class_name\": \"AutoencoderKL\",\n \"_diffusers_version\": \"0.30.0.dev0\",\n \"_name_or_path\": \"../checkpoints/flux-dev\","
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/model_index.json",
"chars": 690,
"preview": "{\n \"_class_name\": \"StableDiffusionXLInpaintPipeline\",\n \"_diffusers_version\": \"0.21.0.dev0\",\n \"_name_or_path\": \"stabil"
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/text_encoder/config.json",
"chars": 746,
"preview": "{\n \"_name_or_path\": \"/home/suraj_huggingface_co/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1."
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/text_encoder_2/config.json",
"chars": 758,
"preview": "{\n \"_name_or_path\": \"/home/suraj_huggingface_co/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1."
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/merges.txt",
"chars": 515308,
"preview": "#version: 0.2\ni n\nt h\na n\nr e\na r\ne r\nth e</w>\nin g</w>\no u\no n\ns t\no r\ne n\no n</w>\na l\na t\ne r</w>\ni t\ni n</w>\nt o</w>\n"
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/special_tokens_map.json",
"chars": 472,
"preview": "{\n \"bos_token\": {\n \"content\": \"<|startoftext|>\",\n \"lstrip\": false,\n \"normalized\": true,\n \"rstrip\": false,\n "
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/tokenizer_config.json",
"chars": 737,
"preview": "{\n \"add_prefix_space\": false,\n \"bos_token\": {\n \"__type\": \"AddedToken\",\n \"content\": \"<|startoftext|>\",\n \"lstri"
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/vocab.json",
"chars": 1050327,
"preview": "{\n \"!\": 0,\n \"!!\": 1443,\n \"!!!\": 11194,\n \"!!!!\": 4003,\n \"!!!!!!!!\": 11281,\n \"!!!!!!!!!!!!!!!!\": 30146,\n \"!!!!!!!!!"
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/merges.txt",
"chars": 515308,
"preview": "#version: 0.2\ni n\nt h\na n\nr e\na r\ne r\nth e</w>\nin g</w>\no u\no n\ns t\no r\ne n\no n</w>\na l\na t\ne r</w>\ni t\ni n</w>\nt o</w>\n"
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/special_tokens_map.json",
"chars": 460,
"preview": "{\n \"bos_token\": {\n \"content\": \"<|startoftext|>\",\n \"lstrip\": false,\n \"normalized\": true,\n \"rstrip\": false,\n "
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/tokenizer_config.json",
"chars": 725,
"preview": "{\n \"add_prefix_space\": false,\n \"bos_token\": {\n \"__type\": \"AddedToken\",\n \"content\": \"<|startoftext|>\",\n \"lstri"
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/vocab.json",
"chars": 1050327,
"preview": "{\n \"!\": 0,\n \"!!\": 1443,\n \"!!!\": 11194,\n \"!!!!\": 4003,\n \"!!!!!!!!\": 11281,\n \"!!!!!!!!!!!!!!!!\": 30146,\n \"!!!!!!!!!"
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/unet/config.json",
"chars": 1932,
"preview": "{\n \"_class_name\": \"UNet2DConditionModel\",\n \"_diffusers_version\": \"0.21.0.dev0\",\n \"_name_or_path\": \"valhalla/sdxl-inpa"
},
{
"path": "backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/vae/config.json",
"chars": 659,
"preview": "{\n \"_class_name\": \"AutoencoderKL\",\n \"_diffusers_version\": \"0.21.0.dev0\",\n \"_name_or_path\": \"madebyollin/sdxl-vae-fp16"
},
{
"path": "backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/scheduler/scheduler_config.json",
"chars": 497,
"preview": "{\n \"_class_name\": \"EDMDPMSolverMultistepScheduler\",\n \"_diffusers_version\": \"0.27.0.dev0\",\n \"algorithm_type\": \"dpmsolv"
},
{
"path": "backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/text_encoder/config.json",
"chars": 560,
"preview": "{\n \"architectures\": [\n \"CLIPTextModel\"\n ],\n \"attention_dropout\": 0.0,\n \"bos_token_id\": 0,\n \"dropout\": 0.0,\n \"eo"
},
{
"path": "backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/text_encoder_2/config.json",
"chars": 570,
"preview": "{\n \"architectures\": [\n \"CLIPTextModelWithProjection\"\n ],\n \"attention_dropout\": 0.0,\n \"bos_token_id\": 0,\n \"dropou"
},
{
"path": "backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/special_tokens_map.json",
"chars": 586,
"preview": "{\n \"bos_token\": {\n \"content\": \"<|startoftext|>\",\n \"lstrip\": false,\n \"normalized\": true,\n \"rstrip\": false,\n "
},
{
"path": "backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/tokenizer_config.json",
"chars": 704,
"preview": "{\n \"add_prefix_space\": false,\n \"added_tokens_decoder\": {\n \"49406\": {\n \"content\": \"<|startoftext|>\",\n \"lst"
},
{
"path": "backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/merges.txt",
"chars": 515308,
"preview": "#version: 0.2\ni n\nt h\na n\nr e\na r\ne r\nth e</w>\nin g</w>\no u\no n\ns t\no r\ne n\no n</w>\na l\na t\ne r</w>\ni t\ni n</w>\nt o</w>\n"
},
{
"path": "backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/special_tokens_map.json",
"chars": 460,
"preview": "{\n \"bos_token\": {\n \"content\": \"<|startoftext|>\",\n \"lstrip\": false,\n \"normalized\": true,\n \"rstrip\": false,\n "
},
{
"path": "backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/vocab.json",
"chars": 1050327,
"preview": "{\n \"!\": 0,\n \"!!\": 1443,\n \"!!!\": 11194,\n \"!!!!\": 4003,\n \"!!!!!!!!\": 11281,\n \"!!!!!!!!!!!!!!!!\": 30146,\n \"!!!!!!!!!"
},
{
"path": "backend/huggingface/runwayml/stable-diffusion-inpainting/config.json",
"chars": 748,
"preview": "{\n \"_class_name\": \"UNet2DConditionModel\",\n \"_diffusers_version\": \"0.6.0.dev0\",\n \"act_fn\": \"silu\",\n \"attention_head_d"
},
{
"path": "extensions-builtin/forge_legacy_preprocessors/annotator/midas/midas/__init__.py",
"chars": 0,
"preview": ""
},
{
"path": "extensions-builtin/forge_legacy_preprocessors/annotator/zoe/zoedepth/models/base_models/midas_repo/input/.placeholder",
"chars": 0,
"preview": ""
},
{
"path": "extensions-builtin/forge_legacy_preprocessors/annotator/zoe/zoedepth/models/base_models/midas_repo/output/.placeholder",
"chars": 0,
"preview": ""
},
{
"path": "extensions-builtin/forge_legacy_preprocessors/annotator/zoe/zoedepth/models/base_models/midas_repo/tf/input/.placeholder",
"chars": 0,
"preview": ""
},
{
"path": "extensions-builtin/forge_legacy_preprocessors/annotator/zoe/zoedepth/models/base_models/midas_repo/tf/output/.placeholder",
"chars": 0,
"preview": ""
},
{
"path": "extensions-builtin/forge_legacy_preprocessors/annotator/zoe/zoedepth/models/base_models/midas_repo/weights/.placeholder",
"chars": 0,
"preview": ""
},
{
"path": "extensions-builtin/forge_preprocessor_inpaint/annotator/lama/saicinpainting/__init__.py",
"chars": 0,
"preview": ""
},
{
"path": "extensions-builtin/forge_preprocessor_inpaint/annotator/lama/saicinpainting/training/__init__.py",
"chars": 0,
"preview": ""
},
{
"path": "extensions-builtin/forge_preprocessor_inpaint/annotator/lama/saicinpainting/training/data/__init__.py",
"chars": 0,
"preview": ""
},
{
"path": "extensions-builtin/forge_preprocessor_inpaint/annotator/lama/saicinpainting/training/losses/__init__.py",
"chars": 0,
"preview": ""
},
{
"path": "extensions-builtin/forge_preprocessor_marigold/marigold/model/__init__.py",
"chars": 0,
"preview": ""
},
{
"path": "localizations/Put localization files here.txt",
"chars": 0,
"preview": ""
},
{
"path": "modules/sd_samplers_compvis.py",
"chars": 0,
"preview": ""
}
]
// ... and 1375 more files (download for full content)
About this extraction
This page contains the full source code of the lllyasviel/stable-diffusion-webui-forge GitHub repository, extracted and formatted as plain text for AI agents and large language models (LLMs). The extraction includes 1490 files (50.8 MB), approximately 4.1M tokens, and a symbol index with 82 extracted functions, classes, methods, constants, and types. Use this with OpenClaw, Claude, ChatGPT, Cursor, Windsurf, or any other AI tool that accepts text input. You can copy the full output to your clipboard or download it as a .txt file.
Extracted by GitExtract — free GitHub repo to text converter for AI. Built by Nikandr Surkov.