The Diffusion Index
← All tools
The Diffusion Index / Training & Fine-tuning / #179
River-Zhang

River-Zhang/ICEdit

by River-Zhang · Training & Fine-tuning · updated 8mo ago

[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!

35
momentum
2,102
stars
111
forks
#179
rank
diffusiondiffusion-modelsdiffusion-transformerditediting-imagegpt4ogpt4oimageimage-editingin-context
View on GitHub →

More in Training & Fine-tuning

civitai
civitai
civitai
15
Training & Fine-tuning
A repository of models, textual inversions, and more
Akegarasu
lora-scripts
Akegarasu
19
Training & Fine-tuning
SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion
transformerlab
transformerlab-app
transformerlab
29
Training & Fine-tuning
The open source research environment for AI researchers to seamlessly train, evaluate, and
XavierXiao
Dreambooth-Stable-Diffusion
XavierXiao
114
Training & Fine-tuning
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion