OSU-NLP-Group/MagicBrush
[NeurIPS'23] "MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing".
This project provides a comprehensive dataset and fine-tuned models for editing images using text instructions. You input a source image and a text command (like "add sunglasses"), and the model generates a new image with the edit applied. This is for researchers, artists, and anyone working with AI image manipulation who needs high-quality, instruction-guided editing capabilities.
403 stars. No commits in the last 6 months.
Use this if you are developing or evaluating AI models for detailed, instruction-based image editing and need a robust, manually-annotated dataset and strong baseline models.
Not ideal if you are looking for a general-purpose image editor for stylistic changes or large-scale region transfers rather than fine-grained real image modifications.
Stars
403
Forks
14
Language
Python
License
—
Category
Last pushed
Feb 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/OSU-NLP-Group/MagicBrush"
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...