Files
SnapOtter/docker/feature-manifest.json
T
SnapOtterandGitHub cf884b52cd fix: offline CodeFormer face-enhance (ship RealESRGAN_x2plus in upscale-enhance bundle) (#433)
* fix: ship RealESRGAN_x2plus.pth in the upscale-enhance bundle for offline CodeFormer

codeformer-pip 0.0.4 downloads RealESRGAN_x2plus.pth at import of
codeformer.app, unconditionally, even though enhance_faces calls
inference_app with background_enhance=False and never uses the background
upsampler. The weight was not bundled, so explicit CodeFormer face-enhance
(enhance-faces model=codeformer) failed in strict offline mode
(SNAPOTTER_ALLOW_MODEL_DOWNLOAD=0) on a host that had never cached it -- the
guard raised before the import could complete.

Add RealESRGAN_x2plus.pth to the upscale-enhance bundle manifest (only that
bundle uses codeformer-pip; photo-restoration uses the CodeFormer ONNX path)
and link it in prepare_codeformer_weights alongside the other three weights,
replacing the download-or-error guard. Once the bundle ships it, the import
resolves offline and strict mode works.

Archive SHA256s updated in a follow-up once the bundle is rebuilt.

Claude-Session: https://claude.ai/code/session_01XGB4pGvTvb7sUX4JN745U7

* fix: require face-detection bundle for enhance-faces + point manifest at the x2plus archives

enhance-faces runs MediaPipe face detection (blaze_face_short_range.tflite)
before CodeFormer/GFPGAN. That model ships in the face-detection bundle, not
the tool's primary upscale-enhance bundle, so a standalone upscale-enhance
install failed face detection (offline: hard error; online: a surprise
download) before reaching the codeformer path. Declare the dependency in
TOOL_EXTRA_BUNDLES like passport-photo does.

Update the upscale-enhance archive SHA256/sizes to the rebuilt bundles that
include RealESRGAN_x2plus.pth (amd64-gpu + arm64-cpu), verified to install and
run enhance-faces model=codeformer in strict offline mode with zero downloads.

Claude-Session: https://claude.ai/code/session_01XGB4pGvTvb7sUX4JN745U7
2026-07-04 16:30:08 +00:00

516 lines
18 KiB
JSON

{
"manifestVersion": 2,
"imageVersion": "2.0.0",
"pythonVersion": { "amd64": "3.12", "arm64": "3.11" },
"basePackages": ["numpy==1.26.4", "Pillow==12.2.0", "opencv-python-headless==4.10.0.84"],
"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"]
}
],
"enablesTools": [
"remove-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
}
],
"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"],
"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
}
],
"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": "089fdecbcd36090013ed4adf3a96650c757ce06871c2e1f1b155ccdd8487e413",
"compressedSize": 5376987856,
"extractedSize": 8455327174
},
"arm64-cpu": {
"file": "v2.0.0/upscale-enhance-arm64-cpu.tar.gz",
"sha256": "b9e948c8308371ccb3defce4323a85884e46d5bde52791115d34d1c1f92e4f23",
"compressedSize": 2335658971,
"extractedSize": 3661453942
}
},
"packages": {
"common": ["codeformer-pip==0.0.4", "huggingface-hub", "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"
}
],
"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": "2ccac73c862f04dafc8d7ecc6543bbe8481b9d796a53a9c4e7cf34e53f261a24",
"compressedSize": 4698091043,
"extractedSize": 8246353920
},
"arm64-cpu": {
"file": "v2.0.0/photo-restoration-arm64-cpu.tar.gz",
"sha256": "13afbaae45d84f1148d00b76a20115283ab3f75d7b2a9e33b940c9bf800b40e1",
"compressedSize": 1367026285,
"extractedSize": 0
}
},
"packages": {
"common": ["codeformer-pip==0.0.4", "huggingface-hub", "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"
}
],
"enablesTools": ["restore-photo"]
},
"ocr": {
"name": "OCR",
"description": "Extract text from images",
"estimatedSize": "3-4 GB",
"archives": {
"amd64-gpu": {
"file": "v2.0.0/ocr-amd64-gpu.tar.gz",
"sha256": "80db475eb442899cedad3590b18f080225deaf50985224b302475fbfdf5883f6",
"compressedSize": 5927587552,
"extractedSize": 9367838720
},
"arm64-cpu": {
"file": "v2.0.0/ocr-arm64-cpu.tar.gz",
"sha256": "569ca2ddad50529c4887da494ca1704bbe719ddc0253a5eb76002a2d87812c60",
"compressedSize": 1974010780,
"extractedSize": 3092260263
}
},
"packages": {
"common": ["huggingface-hub"],
"amd64": [
"paddlepaddle-gpu>=3.2.1 --index-url https://www.paddlepaddle.org.cn/packages/stable/cu126/ --extra-index-url https://pypi.org/simple/",
"paddleocr[doc-parser]>=3.4.0,<3.5.0"
],
"arm64": [
"paddlepaddle>=3.2.1",
"paddleocr[doc-parser]>=3.4.0,<3.5.0",
"protobuf>=4.25.3,<5"
]
},
"pipFlags": {},
"postInstall": [],
"models": [
{
"id": "paddleocr-server-det",
"downloadFn": "hf_snapshot",
"args": ["PaddlePaddle/PP-OCRv5_server_det", "PP-OCRv5_server_det"]
},
{
"id": "paddleocr-server-rec",
"downloadFn": "hf_snapshot",
"args": ["PaddlePaddle/PP-OCRv5_server_rec", "PP-OCRv5_server_rec"]
},
{
"id": "paddleocr-mobile-det",
"downloadFn": "hf_snapshot",
"args": ["PaddlePaddle/PP-OCRv5_mobile_det", "PP-OCRv5_mobile_det"]
},
{
"id": "paddleocr-mobile-rec",
"downloadFn": "hf_snapshot",
"args": ["PaddlePaddle/PP-OCRv5_mobile_rec", "PP-OCRv5_mobile_rec"]
},
{
"id": "paddleocr-latin-rec",
"downloadFn": "hf_snapshot",
"args": ["PaddlePaddle/latin_PP-OCRv5_mobile_rec", "latin_PP-OCRv5_mobile_rec"]
},
{
"id": "paddleocr-korean-rec",
"downloadFn": "hf_snapshot",
"args": ["PaddlePaddle/korean_PP-OCRv5_mobile_rec", "korean_PP-OCRv5_mobile_rec"]
},
{
"id": "paddleocr-textline-ori",
"downloadFn": "hf_snapshot",
"args": ["PaddlePaddle/PP-LCNet_x1_0_textline_ori", "PP-LCNet_x1_0_textline_ori"]
},
{
"id": "paddleocr-vl",
"downloadFn": "hf_snapshot",
"args": ["PaddlePaddle/PaddleOCR-VL-1.5", "PaddleOCR-VL-1.5"]
}
],
"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"]
}
],
"enablesTools": ["transcribe-audio", "auto-subtitles"]
}
}
}