3 people 6a43cc1b77 feat: SOTA AI photo restoration with multi-step pipeline (#58) (#62) ...

Add comprehensive photo restoration tool that chains multiple AI models:
- Scratch/tear/spot detection via morphological analysis (top-hat/black-hat transforms)
- Damage inpainting via LaMa ONNX model (reuses existing infrastructure)
- Face enhancement via CodeFormer ONNX (~377MB, from facefusion/models-3.0.0)
- Noise reduction via OpenCV NLMeans in LAB color space
- Optional B&W auto-colorization via DDColor (reuses existing model)

Settings: 3 restoration modes (Light/Auto/Heavy), individual feature toggles
for scratch removal, face enhancement (with fidelity slider), denoising
(with strength slider), and auto-colorize. Before/after comparison view.

Handles HEIC, HEIF, and all standard formats. Batch processing supported.
No new Python dependencies - reuses onnxruntime, cv2, mediapipe, PIL.

Co-authored-by: stirling-image <stirling-image@users.noreply.github.com>

2026-04-13 21:57:51 +08:00

..

models

feat(noise-removal): SOTA noise removal with 4 quality tiers (#57)

2026-04-13 19:50:23 +08:00

colorize.py

feat: SOTA AI photo colorization with DDColor deep learning model (#57) (#58)

2026-04-13 19:40:55 +08:00

detect_faces.py

feat(smart-crop): overhaul with face detection, social presets, and 3 modes

2026-04-13 00:47:53 +08:00

dispatcher.py

fix: improve AI tool reliability for face detection and background removal (#25)

2026-04-06 22:00:48 +08:00

enhance_faces.py

feat: AI face enhancement with GFPGAN and CodeFormer (#61)

2026-04-13 21:56:59 +08:00

gpu.py

…

inpaint.py

feat(erase-object): overhaul object eraser with LaMa inpainting improvements

2026-04-13 00:48:05 +08:00

noise_removal.py

feat(noise-removal): SOTA noise removal with 4 quality tiers (#57)

2026-04-13 19:50:23 +08:00

ocr_preprocess.py

feat(ocr): add OpenCV preprocessing pipeline for OCR

2026-04-12 18:30:00 +08:00

ocr.py

fix(ocr): fix PaddleOCR crashes, add multi-image and auto-detect language

2026-04-12 23:46:39 +08:00

red_eye_removal.py

feat(red-eye-removal): SOTA red eye removal with MediaPipe Face Mesh + OpenCV LAB correction (#60)

2026-04-13 20:22:30 +08:00

remove_bg.py

feat: add Ultra quality mode with BiRefNet-matting, rename quality tiers

2026-04-12 18:23:09 +08:00

requirements-gpu.txt

feat: AI face enhancement with GFPGAN and CodeFormer (#61)

2026-04-13 21:56:59 +08:00

requirements.txt

feat: AI face enhancement with GFPGAN and CodeFormer (#61)

2026-04-13 21:56:59 +08:00

restore.py

feat: SOTA AI photo restoration with multi-step pipeline (#58) (#62)

2026-04-13 21:57:51 +08:00

upscale.py

fix(upscale): overhaul UI, fix AI pipeline bugs, add format support

2026-04-12 21:22:55 +08:00