Home Projects ICEdit
ICEdit
Python

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!

by River-Zhang · GitHub
Stars
Forks
Created
Last commit
Category
Language
diffusiondiffusion-modelsdiffusion-transformerPython
View on GitHub
In plain words

Edit images based on instructions using a model that requires minimal training data.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
ICEdit — GitHub preview card
📈 Star history
2 1022 101
2026-07-072026-08-31
📈 Track ICEdit

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

[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!

ICEdit has 2.1k stars on GitHub. It has been forked 111 times. ICEdit is written mainly in Python. It has been in active development since 2025. Its main topics are diffusion, diffusion-models, diffusion-transformer, dit.

Frequently asked questions

What is 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!

Is ICEdit open source?

ICEdit is an open-source project.

Is ICEdit free?

Yes. ICEdit is free and open source — you can use, modify and self-host it.

What language is ICEdit written in?

ICEdit is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — ICEdit

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=river-zhang-icedit)](https://olud.ai/project/river-zhang-icedit.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
InfiniteYou
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
2.7k · diffusers
sharesditdiffusion-transformer
fantasy-talking
[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthes…
1.6k · diffusion
sharesdiffusion-transformerdiffusion
DiT-Extrapolation
Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion T…
820 · cogvideox
sharesdiffusion-transformerdiffusion
HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model
12.3k · diffusion-models
sharesdiffusion-transformerdiffusion-models
REPA
[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easi…
1.7k · diffusion
sharesdiffusiondiffusion-models
UNO
[ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditi…
1.4k · diffusion
sharesdiffusion-transformerdiffusion
HunyuanImage-2.1
HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generatio…
672 · aigc
sharesdiffusion-transformerdiffusion-models
Voost
[SIGGRAPH Asia 25] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtua…
340 · diffusion-models
sharesdiffusion-transformerdiffusion-models
ComfyUI-LTXVideo
LTX-Video Support for ComfyUI
4k · comfyui
sharesditdiffusion-models
blended-latent-diffusion
Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]
631 · computer-vision
sharesdiffusiondiffusion-models

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.