yuanze-lin/Learnable_Regions
[CVPR 2024] Official code for "Text-Driven Image Editing via Learnable Regions"
This project helps graphic designers and artists quickly modify images using simple text descriptions, without needing to manually select specific areas. You provide an existing image and a text prompt describing the desired change (like "add flowers to the tree"), and the tool generates a new version of the image with those modifications applied. It's ideal for anyone who wants to efficiently iterate on visual concepts or make precise, localized edits.
228 stars. No commits in the last 6 months.
Use this if you need to make specific, text-driven edits to images without drawing masks or manually selecting regions, and you value realism and fidelity in the output.
Not ideal if you prefer pixel-level control with traditional image editing software or need to make global, non-localized changes to an entire image without specific object manipulation.
Stars
228
Forks
24
Language
Python
License
MIT
Category
Last pushed
Sep 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yuanze-lin/Learnable_Regions"
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...