bytedance/SuperEdit
[ICCV 2025] Code & Data for: SuperEdit - Rectifying and Facilitating Supervision for Instruction-Based Image Editing
This project helps image editors and content creators refine AI-generated images based on text instructions. It takes an original image and a text instruction for editing, and produces a more accurate, edited image by improving how the AI understands and applies your commands. This is ideal for professionals like graphic designers, marketers, or anyone who uses AI for visual content creation.
163 stars. No commits in the last 6 months.
Use this if you need to create high-quality, instruction-based image edits and frequently encounter AI models misinterpreting your text prompts, leading to inaccurate results.
Not ideal if you primarily need simple, manual image adjustments or if your workflow does not involve AI-driven text-to-image editing.
Stars
163
Forks
8
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/bytedance/SuperEdit"
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...