[
{
"path": ".gitignore",
"content": "# Byte-compiled / optimized / DLL files\n__pycache__/\n*.py[cod]\n*$py.class\n\n# models\nmodels/\n\n# C extensions\n*.so\n\n# Distribution / packaging\n.Python\nbuild/\ndevelop-eggs/\ndist/\ndownloads/\neggs/\n.eggs/\nlib/\nlib64/\nparts/\nsdist/\nvar/\nwheels/\nshare/python-wheels/\n*.egg-info/\n.installed.cfg\n*.egg\nMANIFEST\n\n# PyInstaller\n# Usually these files are written by a python script from a template\n# before PyInstaller builds the exe, so as to inject date/other infos into it.\n*.manifest\n*.spec\n\n# Installer logs\npip-log.txt\npip-delete-this-directory.txt\n\n# Unit test / coverage reports\nhtmlcov/\n.tox/\n.nox/\n.coverage\n.coverage.*\n.cache\nnosetests.xml\ncoverage.xml\n*.cover\n*.py,cover\n.hypothesis/\n.pytest_cache/\ncover/\n\n# Translations\n*.mo\n*.pot\n\n# Django stuff:\n*.log\nlocal_settings.py\ndb.sqlite3\ndb.sqlite3-journal\n\n# Flask stuff:\ninstance/\n.webassets-cache\n\n# Scrapy stuff:\n.scrapy\n\n# Sphinx documentation\ndocs/_build/\n\n# PyBuilder\n.pybuilder/\ntarget/\n\n# Jupyter Notebook\n.ipynb_checkpoints\n\n# IPython\nprofile_default/\nipython_config.py\n\n# pyenv\n# For a library or package, you might want to ignore these files since the code is\n# intended to run in multiple environments; otherwise, check them in:\n# .python-version\n\n# pipenv\n# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.\n# However, in case of collaboration, if having platform-specific dependencies or dependencies\n# having no cross-platform support, pipenv may install dependencies that don't work, or not\n# install all needed dependencies.\n#Pipfile.lock\n\n# poetry\n# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.\n# This is especially recommended for binary packages to ensure reproducibility, and is more\n# commonly ignored for libraries.\n# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control\n#poetry.lock\n\n# pdm\n# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.\n#pdm.lock\n# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it\n# in version control.\n# https://pdm.fming.dev/#use-with-ide\n.pdm.toml\n\n# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm\n__pypackages__/\n\n# Celery stuff\ncelerybeat-schedule\ncelerybeat.pid\n\n# SageMath parsed files\n*.sage.py\n\n# Environments\n.env\n.venv\nenv/\nvenv/\nENV/\nenv.bak/\nvenv.bak/\n\n# Spyder project settings\n.spyderproject\n.spyproject\n\n# Rope project settings\n.ropeproject\n\n# mkdocs documentation\n/site\n\n# mypy\n.mypy_cache/\n.dmypy.json\ndmypy.json\n\n# Pyre type checker\n.pyre/\n\n# pytype static type analyzer\n.pytype/\n\n# Cython debug symbols\ncython_debug/\n\n# PyCharm\n# JetBrains specific template is maintained in a separate JetBrains.gitignore that can\n# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore\n# and can be added to the global gitignore or merged into this file. For a more nuclear\n# option (not recommended) you can uncomment the following to ignore the entire idea folder.\n#.idea/\n"
},
{
"path": "LICENSE",
"content": "MIT License\n\nCopyright (c) 2023 spacepxl\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.\n"
},
{
"path": "README.md",
"content": "## ComfyUI-Image-Filters\n\nStarted as just some image processing nodes, but now more of a kitchen sink nodepack\n\nTwo install batch files are provided, `install.bat` which only installs requirements, and `import_error_install.bat`, which uninstalls all versions of opencv then reinstalls all 4 variants with matching version (use this if you get import errors relating to opencv or cv2, which are caused by manager or other node packs installing different variants and/or versions.)\n\nOr if you want to manage requirements manually, the only opencv variant you actually need is `opencv-contrib-python`, it covers all opencv requirements.\n\n## Nodes\n\nLatent
\n\n### AdaIN Latent\n\nNormalizes latents to the mean and std dev of a reference input. Useful for getting rid of color shift from high denoise strength, or matching color to a reference in general.\n\n### AdaIN Filter Latent\n\nSame as AdaIN Latent, but with a spatial filter instead of the full frame, works like a latent color match.\n\n### Batch Normalize Latent\n\nNormalizes each frame in a batch to the overall mean and std dev, good for removing overall brightness flickering.\n\n### Clamp Outliers\n\nClamps latents that are more than n standard deviations away from the mean. Could help with fireflies or stray noise that disrupt the VAE decode.\n\n### Upscale Hunyuan3Dv2 Latent By\n\nNearest Neighbor upscaling for Hy3D latents, might be useful for hires fix.\n\n### Latent Normalize/Shuffle\n\nCan help break up residual image information in inversion noise.\n\n### RandnLikeLatent\n\nCreate random noise in the same shape as the input latent, works with any latent. Useful for noise injection or other times when you just want to control noise manually.\n\n### Offset Latent Image\n\nCreate an empty latent image with custom values, for offset noise with per-channel control. Can be combined with Latent Stats to get channel values.\n\n### Sharpen Filter (Latent)\n\nIncreases local contrast between latent \"pixels\" with an image sharpening filter.\n\nImage
\n\n### AdaIN Image\n\nNormalizes images to the mean and std dev of a reference input. Useful for getting rid of color shift from high denoise strength, or matching color to a reference in general.\n\n### Batch Align (RAFT)\n\nUse RAFT motion vectors to warp align images\n\n### Batch Average Image\n\nReturns the single average image of a batch.\n\n### Batch Normalize Image\n\nNormalizes each frame in a batch to the overall mean and std dev, good for removing overall brightness flickering.\n\n### BetterFilmGrain\n\nYet another film grain node, but this one looks better (realistic grain structure, no pixel-perfect RGB glitter, natural luminance/intensity response) and is 10x faster than the next best option (ProPostFilmGrain).\n\n### Bilateral Filter Image\n\nApplies a bilateral filter, can be used to remove noise or high frequency details while preserving edges\n\n### Blur Image (Fast)\n\nBlurs images using opencv gaussian blur, which is >100x faster than comfy image blur. Supports larger blur radius, and separate x/y controls.\n\n### Clamp Image\n\nClamps image values outside of blackpoint/whitepoint range\n\n### Color Match Image\n\nMatch image color to reference image, using overall mean or blurred image (frequency separation)\n\n### Convert Normals\n\nTranslate between different normal map color spaces, with optional normalization fix and black region fix.\n\n### Depth to Normals\n\nConverts depthmap to normal map\n\n### Difference Checker\n\nAbsolute value of the difference between inputs, with a multiplier to boost dark values for easier viewing. Alternative to the vanilla merge difference node, which is only subtraction without the abs()\n\n### Enhance Detail\n\nIncrease or decrease details in an image or batch of images using a guided filter (as opposed to the typical gaussian blur used by most sharpening filters)\n\n### Exposure Adjust\n\nLinear exposure adjustment in f-stops, with optional tonemap.\n\n### Frequency Separate/Combine\n\nFor manual frequency separation workflows\n\n### Game of Life\n\nRuns the Game of Life simulation with optional mask input for starting condition\n\n### Guided Filter Image\n\nUse a guided filter to blur an image or mask based on RGB color similarity. Works best with a strong color separation between FG and BG.\n\n### Image Constant Color (RGB/HSV)\n\nCreate images of any solid color, from either RGB or HSV values\n\n### Image Matting\n\nTakes an image and trimap/mask, and refines the matte edges with [closed-form matting](https://github.com/pymatting/pymatting). Optionally extracts the foreground and background colors as well. Good for cleaning up SAM segments or hand drawn masks.\n\n### Keyer\n\nBasic image keyer with luma/sat/channel/greenscreen/etc options\n\n### Median Filter Image\n\nApplies a median filter to remove high frequency information from images, useful for frequency separation workflows\n\n### Normal Map (Simple)\n\nSimple high-frequency normal map from Scharr operator\n\n### Relight (Simple)\n\nBasic dot product (Lambertian) relighting from a normal map\n\n### Remap Range\n\nFits the color range of an image to a new blackpoint and whitepoint (clamped)\n\n### Restore Detail\n\nTransfers details from one image to another using frequency separation. Useful for restoring the lost details from IC-Light or other img2img workflows. Has options for add/subtract method (fewer artifacts, but mostly ignores highlights) or divide/multiply (more natural but can create artifacts in areas that go from dark to bright), and either gaussian blur or guided filter (prevents oversharpened edges)\n\n### Shuffle Channels\n\nMove channels around at will.\n\n### Tonemap / UnTonemap\n\nApply or remove a log + contrast curve tonemap\n\nApply tonemap:\n```\npower = 1.7\nSLog3R = clamp((log10((r + 0.01)/0.19) * 261.5 + 420) / 1023, 0, 1)\nSLog3G = clamp((log10((g + 0.01)/0.19) * 261.5 + 420) / 1023, 0, 1)\nSLog3B = clamp((log10((b + 0.01)/0.19) * 261.5 + 420) / 1023, 0, 1)\n\nr = r > 0.06 ? pow(1 / (1 + (1 / pow(SLog3R / (1 - SLog3R), power))), power) : r\ng = g > 0.06 ? pow(1 / (1 + (1 / pow(SLog3G / (1 - SLog3G), power))), power) : g\nb = b > 0.06 ? pow(1 / (1 + (1 / pow(SLog3B / (1 - SLog3B), power))), power) : b\n```\n\nRemove tonemap:\n```\npower = 1.7\nSR = 1 / (1 + pow((-1/pow(r, 1/power)) * (pow(r, 1/power) - 1), 1/power))\nSG = 1 / (1 + pow((-1/pow(g, 1/power)) * (pow(g, 1/power) - 1), 1/power))\nSB = 1 / (1 + pow((-1/pow(b, 1/power)) * (pow(b, 1/power) - 1), 1/power))\n\nr = r > 0.06 ? pow(10, (SR * 1023 - 420)/261.5) * 0.19 - 0.01 : r\ng = g > 0.06 ? pow(10, (SG * 1023 - 420)/261.5) * 0.19 - 0.01 : g\nb = b > 0.06 ? pow(10, (SB * 1023 - 420)/261.5) * 0.19 - 0.01 : b\n```\n\n### JitterImage, UnJitterImage, BatchAverageUnJittered\n\nFor supersampling/antialiasing workflows.\n\n### Extract N Frames, Merge Frames By Index\n\nFor processing a smaller number of frames evenly distributed across a larger batch/video, then merging them back into the full batch\n\nMask
\n\n### Blur Mask (Fast)\n\nSame as Blur Image (Fast) but for masks instead of images.\n\n### Dilate/Erode Mask\n\nDilate or erode masks, with either a box or circle filter.\n\n### Mask Clean\n\nClean up holes and near-solid areas in a matte.\n\n### Pack Video Mask\n\nCompresses the frames of a video mask to match video VAE latent frames, to work around comfyui's naive temporal resizing of masks.\n\nConditioning
\n\n### Conditioning Subtract\n\nTakes the difference of two text conditions, can have interesting effects that are different from negative prompts.\n\n### Inpaint Condition Encode/Apply\n\nSeparates the VAE encode from the conditioning so you don't have to re-encode latents every time you change a prompt.\n\n### IP2P Conditioning Advanced\n\nSeparates the VAE encode from the conditioning so you don't have to re-encode latents every time you change a prompt.\n\nSampling
\n\n### Custom Noise\n\nUse any latent as the noise for SamplerCustomAdvanced.\n\nUtils
\n\n### Latent Stats\n\nGet/print some stats about the latents (dimensions, and per-channel mean, std dev, min, and max)\n\n### Model Test\n\nDebugging node for examining model structure\n\n### Print Sigmas\n\nPrints the noise schedule sigma values to see what a scheduler is doing\n\n### Visualize Latents\n\nShows the latent channels as a grid image\n\n