External/SnapOtter
1
0
Fork 0
mirror of https://github.com/snapotter-hq/SnapOtter.git synced 2026-08-03 07:46:42 +02:00
Code Issues Packages Projects Releases Wiki Activity
Files
991c981529c81ebb719199aba084db4c2d9a7c6f
SnapOtter/docker/feature-manifest.json
T
SnapOtterandGitHub 991c981529 fix: make OCR portable and reliable across AMD64 and ARM64 (#519) 
* fix: make OCR portable and reliable

* fix: harden OCR installation portability

* fix: pin OCR partials across downloads

* fix: make OCR execution reliably asynchronous

* fix: harden OCR portability and docs routes

* fix: preserve decoder and docs safeguards
2026-07-15 03:34:24 +08:00

500 lines
17 KiB
JSON
Raw Blame History

{
"manifestVersion": 2,
"imageVersion": "2.0.0",
"pythonVersion": { "amd64": "3.12", "arm64": "3.11" },
"basePackages": [
"numpy==1.26.4",
"Pillow==12.3.0",
"opencv-python-headless==4.10.0.84",
"huggingface-hub[hf_xet,hf_transfer]==0.36.2"
],
"constraints": [
"numpy==1.26.4",
"scipy==1.12.0",
"scikit-learn==1.4.2",
"scikit-image==0.24.0",
"pandas==2.2.2"
],
"bundleRepo": "deepsafe/feature-bundles",
"bundles": {
"background-removal": {
"name": "Background Removal",
"description": "Remove image backgrounds with AI",
"estimatedSize": "4-5 GB",
"archives": {
"amd64-gpu": {
"file": "v2.0.0/background-removal-amd64-gpu.tar.gz",
"sha256": "a1dfbdd5862fd32c7719ca79b0c7e4b76a327330a5991ddad98a2761abca10cb",
"compressedSize": 4808242472,
"extractedSize": 0
},
"arm64-cpu": {
"file": "v2.0.0/background-removal-arm64-cpu.tar.gz",
"sha256": "cbb570b81bfd740dd05e265dd8c93ade53a9f41fdd30cc8b3fbc47a8daa824af",
"compressedSize": 4631430295,
"extractedSize": 0
}
},
"packages": {
"common": ["rembg==2.0.62"],
"amd64": ["onnxruntime-gpu==1.20.1", "mediapipe>=0.10.21"],
"arm64": ["onnxruntime==1.20.1", "mediapipe>=0.10.18"]
},
"pipFlags": {},
"postInstall": [],
"models": [
{
"id": "rembg-u2net",
"downloadFn": "rembg_session",
"args": ["u2net"]
},
{
"id": "rembg-isnet-general-use",
"downloadFn": "rembg_session",
"args": ["isnet-general-use"]
},
{
"id": "rembg-bria-rmbg",
"downloadFn": "rembg_session",
"args": ["bria-rmbg"]
},
{
"id": "rembg-birefnet-general-lite",
"downloadFn": "rembg_session",
"args": ["birefnet-general-lite"]
},
{
"id": "rembg-birefnet-portrait",
"downloadFn": "rembg_session",
"args": ["birefnet-portrait"]
},
{
"id": "rembg-birefnet-general",
"downloadFn": "rembg_session",
"args": ["birefnet-general"]
},
{
"id": "rembg-birefnet-matting",
"downloadFn": "rembg_session",
"args": ["birefnet-matting"]
},
{
"id": "rembg-birefnet-hr-matting",
"downloadFn": "rembg_session",
"args": ["birefnet-hr-matting"]
}
],
"smokeImports": ["rembg", "onnxruntime"],
"enablesTools": [
"remove-background",
"remove-gif-background",
"passport-photo",
"transparency-fixer",
"background-replace",
"blur-background"
]
},
"face-detection": {
"name": "Face Detection",
"description": "Detect and blur faces, fix red-eye, smart crop",
"estimatedSize": "200-300 MB",
"archives": {
"amd64-gpu": {
"file": "v2.0.0/face-detection-amd64-gpu.tar.gz",
"sha256": "0ee28b86dac88c60e005604ba0595746f455ec97f08d0c8307ba9b57e131bc7f",
"compressedSize": 75358868,
"extractedSize": 209838080
},
"arm64-cpu": {
"file": "v2.0.0/face-detection-arm64-cpu.tar.gz",
"sha256": "8ad922514aba1721de154d370f9335f78c5ce5aceade5b19515e0192d4367909",
"compressedSize": 222878753,
"extractedSize": 704276480
}
},
"packages": {
"common": [],
"amd64": ["mediapipe>=0.10.21"],
"arm64": ["mediapipe>=0.10.18"]
},
"pipFlags": {},
"postInstall": [],
"models": [
{
"id": "mediapipe-face-detector",
"url": "https://storage.googleapis.com/mediapipe-models/face_detector/blaze_face_short_range/float16/latest/blaze_face_short_range.tflite",
"path": "mediapipe/blaze_face_short_range.tflite",
"minSize": 100000
},
{
"id": "mediapipe-face-landmarker",
"url": "https://storage.googleapis.com/mediapipe-models/face_landmarker/face_landmarker/float16/latest/face_landmarker.task",
"path": "mediapipe/face_landmarker.task",
"minSize": 1000000
}
],
"smokeImports": ["mediapipe"],
"enablesTools": ["blur-faces", "red-eye-removal", "smart-crop"]
},
"object-eraser-colorize": {
"name": "Object Eraser & Colorize",
"description": "Erase objects from photos and colorize B&W images",
"estimatedSize": "1-2 GB",
"archives": {
"amd64-gpu": {
"file": "v2.0.0/object-eraser-colorize-amd64-gpu.tar.gz",
"sha256": "a3f6cd2eca9e5dd907497d0d58ca5f6532887bb748e4062de0f4fb9815782c31",
"compressedSize": 1545472964,
"extractedSize": 2249379840
},
"arm64-cpu": {
"file": "v2.0.0/object-eraser-colorize-arm64-cpu.tar.gz",
"sha256": "252c0b4fc4ca6f807b2b93038a98469323d906d5c4d75df88e9f47497d30e67c",
"compressedSize": 1263259968,
"extractedSize": 1464884023
}
},
"packages": {
"common": ["huggingface-hub[hf_xet]==0.36.2"],
"amd64": ["onnxruntime-gpu==1.20.1"],
"arm64": ["onnxruntime==1.20.1", "protobuf>=4.25.3,<5"]
},
"pipFlags": {},
"postInstall": [],
"models": [
{
"id": "lama-onnx",
"downloadFn": "hf_snapshot",
"args": ["Carve/LaMa-ONNX", "lama"],
"file": "lama_fp32.onnx",
"path": "lama/lama_fp32.onnx",
"minSize": 100000000
},
{
"id": "ddcolor-onnx",
"downloadFn": "hf_snapshot",
"args": ["facefusion/models-3.0.0", "ddcolor"],
"file": "ddcolor.onnx",
"path": "ddcolor/ddcolor.onnx",
"minSize": 50000000
},
{
"id": "opencv-colorize-prototxt",
"url": "https://raw.githubusercontent.com/richzhang/colorization/caffe/colorization/models/colorization_deploy_v2.prototxt",
"path": "colorize-opencv/colorization_deploy_v2.prototxt",
"minSize": 0
},
{
"id": "opencv-colorize-caffemodel",
"downloadFn": "hf_snapshot",
"args": ["BilalSardar/Black-N-White-To-Color", "colorize-opencv"],
"file": "colorization_release_v2.caffemodel",
"path": "colorize-opencv/colorization_release_v2.caffemodel",
"minSize": 100000000,
"repoType": "space"
},
{
"id": "opencv-colorize-points",
"url": "https://raw.githubusercontent.com/richzhang/colorization/caffe/colorization/resources/pts_in_hull.npy",
"path": "colorize-opencv/pts_in_hull.npy",
"minSize": 0
}
],
"smokeImports": ["onnxruntime"],
"enablesTools": ["erase-object", "colorize", "ai-canvas-expand"]
},
"upscale-enhance": {
"name": "Upscale & Enhance",
"description": "AI upscaling, face enhancement, and noise removal",
"estimatedSize": "4-5 GB",
"archives": {
"amd64-gpu": {
"file": "v2.0.0/upscale-enhance-amd64-gpu.tar.gz",
"sha256": "b725a0b18a8295cb87e15f79b31c294f1de98101dedd76389728300a8d377a15",
"compressedSize": 5358573124,
"extractedSize": 8406943960
},
"arm64-cpu": {
"file": "v2.0.0/upscale-enhance-arm64-cpu.tar.gz",
"sha256": "bfb25ff1468d426ba6a125632beabece11e1afebfa6a3adefc64f7b81d7bf469",
"compressedSize": 2319501276,
"extractedSize": 3661453942
}
},
"packages": {
"common": [
"codeformer-pip==0.0.4",
"huggingface-hub[hf_xet]==0.36.2",
"einops",
"setuptools<75"
],
"amd64": [
"torch==2.7.0+cu126 torchvision==0.22.0+cu126 --index-url https://download.pytorch.org/whl/cu126",
"lpips",
"basicsr==1.4.2",
"realesrgan==0.3.0",
"mediapipe>=0.10.21"
],
"arm64": [
"torch==2.7.0 torchvision==0.22.0 --index-url https://download.pytorch.org/whl/cpu",
"lpips",
"basicsr==1.4.2",
"realesrgan==0.3.0",
"mediapipe>=0.10.18"
]
},
"pipFlags": {
"codeformer-pip==0.0.4": "--no-deps",
"basicsr==1.4.2": "--no-build-isolation"
},
"postInstall": ["numpy==1.26.4"],
"models": [
{
"id": "realesrgan-x4plus",
"url": "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth",
"path": "realesrgan/RealESRGAN_x4plus.pth",
"minSize": 60000000
},
{
"id": "realesrgan-x2plus",
"url": "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth",
"path": "realesrgan/RealESRGAN_x2plus.pth",
"minSize": 60000000
},
{
"id": "gfpgan-v1.3",
"url": "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth",
"path": "gfpgan/GFPGANv1.3.pth",
"minSize": 300000000
},
{
"id": "codeformer-pth",
"url": "https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth",
"path": "codeformer/codeformer.pth",
"minSize": 350000000
},
{
"id": "codeformer-onnx",
"downloadFn": "hf_snapshot",
"args": ["facefusion/models-3.0.0", "codeformer"],
"file": "codeformer.onnx",
"path": "codeformer/codeformer.onnx",
"minSize": 100000000
},
{
"id": "facexlib-detection",
"url": "https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth",
"path": "gfpgan/facelib/detection_Resnet50_Final.pth",
"minSize": 100000000
},
{
"id": "facexlib-parsing",
"url": "https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth",
"path": "gfpgan/facelib/parsing_parsenet.pth",
"minSize": 80000000
},
{
"id": "scunet-color-real",
"url": "https://github.com/cszn/KAIR/releases/download/v1.0/scunet_color_real_psnr.pth",
"path": "scunet/scunet_color_real_psnr.pth",
"minSize": 3000000
},
{
"id": "nafnet-sidd",
"downloadFn": "hf_snapshot",
"args": ["mikestealth/nafnet-models", "nafnet"],
"file": "NAFNet-SIDD-width64.pth",
"path": "nafnet/NAFNet-SIDD-width64.pth",
"minSize": 60000000
}
],
"patches": [
{
"file": "basicsr/data/degradations.py",
"search": "from torchvision.transforms.functional_tensor import rgb_to_grayscale",
"replace": "from torchvision.transforms.functional import rgb_to_grayscale"
}
],
"smokeImports": ["torch", "torchvision"],
"enablesTools": ["upscale", "enhance-faces", "noise-removal"]
},
"photo-restoration": {
"name": "Photo Restoration",
"description": "Restore old or damaged photos",
"estimatedSize": "800 MB - 1 GB",
"archives": {
"amd64-gpu": {
"file": "v2.0.0/photo-restoration-amd64-gpu.tar.gz",
"sha256": "4747953db35c71b83db19ce12cc6c591730f0cb9f64621f239db17ae3e3563fd",
"compressedSize": 4680254837,
"extractedSize": 8172949791
},
"arm64-cpu": {
"file": "v2.0.0/photo-restoration-arm64-cpu.tar.gz",
"sha256": "261a27a176b9f3e76d8cd92576b73a1c014b19e87b4f16e58ed46d17c77697c0",
"compressedSize": 1361837793,
"extractedSize": 2584214411
}
},
"packages": {
"common": ["codeformer-pip==0.0.4", "huggingface-hub[hf_xet]==0.36.2", "setuptools<75"],
"amd64": [
"onnxruntime-gpu==1.20.1",
"mediapipe>=0.10.21",
"torch==2.7.0+cu126 torchvision==0.22.0+cu126 --index-url https://download.pytorch.org/whl/cu126",
"lpips",
"basicsr==1.4.2",
"realesrgan==0.3.0"
],
"arm64": [
"torch==2.7.0 torchvision==0.22.0 --index-url https://download.pytorch.org/whl/cpu",
"onnxruntime==1.20.1",
"mediapipe>=0.10.18",
"lpips",
"basicsr==1.4.2",
"realesrgan==0.3.0"
]
},
"pipFlags": {
"codeformer-pip==0.0.4": "--no-deps",
"basicsr==1.4.2": "--no-build-isolation"
},
"postInstall": ["numpy==1.26.4"],
"models": [
{
"id": "lama-onnx",
"downloadFn": "hf_snapshot",
"args": ["Carve/LaMa-ONNX", "lama"],
"file": "lama_fp32.onnx",
"path": "lama/lama_fp32.onnx",
"minSize": 100000000
},
{
"id": "codeformer-onnx",
"downloadFn": "hf_snapshot",
"args": ["facefusion/models-3.0.0", "codeformer"],
"file": "codeformer.onnx",
"path": "codeformer/codeformer.onnx",
"minSize": 100000000
},
{
"id": "realesrgan-x4plus",
"url": "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth",
"path": "realesrgan/RealESRGAN_x4plus.pth",
"minSize": 60000000
},
{
"id": "facexlib-detection",
"url": "https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth",
"path": "gfpgan/facelib/detection_Resnet50_Final.pth",
"minSize": 100000000
},
{
"id": "facexlib-parsing",
"url": "https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth",
"path": "gfpgan/facelib/parsing_parsenet.pth",
"minSize": 80000000
},
{
"id": "mediapipe-face-detector",
"url": "https://storage.googleapis.com/mediapipe-models/face_detector/blaze_face_short_range/float16/latest/blaze_face_short_range.tflite",
"path": "mediapipe/blaze_face_short_range.tflite",
"minSize": 100000
},
{
"id": "mediapipe-face-landmarker",
"url": "https://storage.googleapis.com/mediapipe-models/face_landmarker/face_landmarker/float16/latest/face_landmarker.task",
"path": "mediapipe/face_landmarker.task",
"minSize": 1000000
},
{
"id": "scunet-color-real",
"url": "https://github.com/cszn/KAIR/releases/download/v1.0/scunet_color_real_psnr.pth",
"path": "scunet/scunet_color_real_psnr.pth",
"minSize": 3000000
}
],
"patches": [
{
"file": "basicsr/data/degradations.py",
"search": "from torchvision.transforms.functional_tensor import rgb_to_grayscale",
"replace": "from torchvision.transforms.functional import rgb_to_grayscale"
}
],
"smokeImports": ["onnxruntime", "torch", "mediapipe"],
"enablesTools": ["restore-photo"]
},
"ocr": {
"name": "OCR",
"description": "High-accuracy local OCR for images and PDFs",
"estimatedSize": "~208-234 MiB download / ~409-488 MiB installed",
"runtimeFormatVersion": 3,
"runtimeFamily": "ocr",
"modelManifest": "docker/ocr-runtime-models.json",
"targets": {
"linux-amd64-cpu-py312": {
"file": "v3/ocr-linux-amd64-cpu-py312.tar.gz",
"compressedSizeEstimate": 244622462,
"extractedSizeEstimate": 510762511,
"sizeKind": "measured-estimate",
"minimumMemoryBytes": 4294967296,
"requirements": "docker/ocr-runtime-requirements-amd64.txt"
},
"linux-arm64-cpu-py311": {
"file": "v3/ocr-linux-arm64-cpu-py311.tar.gz",
"compressedSizeEstimate": 218031562,
"extractedSizeEstimate": 428565655,
"sizeKind": "measured-estimate",
"minimumMemoryBytes": 4294967296,
"requirements": "docker/ocr-runtime-requirements-arm64.txt"
}
},
"packages": {
"common": ["rapidocr==3.9.1", "onnxruntime==1.20.1"],
"amd64": [],
"arm64": []
},
"pipFlags": {},
"postInstall": [],
"models": [],
"smokeImports": ["rapidocr", "onnxruntime"],
"enablesTools": ["ocr", "ocr-pdf"]
},
"transcription": {
"name": "Transcription",
"description": "Speech to text for audio and video (subtitles)",
"estimatedSize": "~600 MB",
"archives": {
"amd64-gpu": {
"file": "v2.0.0/transcription-amd64-gpu.tar.gz",
"sha256": "3033d480c6183df66855d78c355233dbc86a754d07414e544e1df1038337c9e1",
"compressedSize": 559189061,
"extractedSize": 845987840
},
"arm64-cpu": {
"file": "v2.0.0/transcription-arm64-cpu.tar.gz",
"sha256": "07088951300dec14b80f4723a3d5bd968574ce2650259be3fd487e7abb47e120",
"compressedSize": 528491203,
"extractedSize": 741534382
}
},
"packages": {
"common": ["faster-whisper>=1.0.0"],
"amd64": [],
"arm64": ["protobuf>=4.25.3,<5"]
},
"pipFlags": {},
"postInstall": [],
"models": [
{
"id": "faster-whisper-small",
"downloadFn": "hf_snapshot",
"args": ["Systran/faster-whisper-small", "faster-whisper-small"]
}
],
"smokeImports": ["faster_whisper", "ctranslate2"],
"enablesTools": ["transcribe-audio", "auto-subtitles"]
}
}
}
Reference in New Issue View Git Blame Copy Permalink