River-Zhang/ICEdit

[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!

48
/ 100
Emerging

This project helps graphic designers, digital artists, and marketers quickly modify existing images using text instructions. You input an image and a text prompt describing the desired change, and it outputs an edited image that precisely follows your instructions. This tool is ideal for anyone needing to iterate rapidly on visual content without complex manual editing.

2,083 stars.

Use this if you need to make precise, instruction-based edits to images efficiently, even with limited computing resources.

Not ideal if you need to generate images from scratch or perform very subtle, artistic touch-ups that require fine-grained manual control.

image-editing digital-art graphic-design visual-content-creation marketing-assets
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 17 / 25

How are scores calculated?

Stars

2,083

Forks

114

Language

Python

License

Last pushed

Dec 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/River-Zhang/ICEdit"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.