andreas128/RePaint
Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022
RePaint helps graphic designers, photographers, or visual content creators fill in missing or damaged parts of an image naturally. You provide an image with masked-out (blue) areas and RePaint intelligently generates the missing pixels, creating a complete and harmonious image. It's ideal for restoring old photos, removing unwanted objects, or expanding image backgrounds.
2,247 stars. No commits in the last 6 months.
Use this if you need to seamlessly reconstruct missing regions in various types of images, like faces, landscapes, or general scenes.
Not ideal if you need to train a diffusion model from scratch, as RePaint focuses on using pre-trained models for inference and inpainting.
Stars
2,247
Forks
197
Language
Python
License
—
Category
Last pushed
Aug 20, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/andreas128/RePaint"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bytedance/InfiniteYou
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
River-Zhang/ICEdit
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image...
muzishen/IMAGHarmony
🧩 IMAGHarmony 🧩: Controllable image editing with consistent object quantity and layout. A...
AMAP-ML/FE2E
[CVPR 2026] Beyond Generation: Advancing Image Editing Priors for Depth and Normal Estimation
TencentARC/BrushNet
[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting...