aim-uofa/OIR
[ICLR 2024] Official PyTorch/Diffusers implementation of "Object-aware Inversion and Reassembly for Image Editing"
This tool helps creative professionals and researchers precisely edit specific objects within images generated by AI, like Stable Diffusion. You provide an AI-generated image and tell the system what objects to change and how, receiving back an edited image where only the targeted objects have been modified, leaving the rest of the image consistent. This is designed for graphic designers, digital artists, and AI researchers who need fine-grained control over AI-generated visual content.
No commits in the last 6 months.
Use this if you need to modify individual objects in an AI-generated image without altering the background or other elements, ensuring a cohesive and realistic final output.
Not ideal if you are looking for broad, stylistic image transformations or do not need object-level precision in your edits.
Stars
88
Forks
2
Language
Python
License
—
Category
Last pushed
Aug 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/aim-uofa/OIR"
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...