River-Zhang/ICEdit

by River-Zhang · Training & Fine-tuning · updated 9mo 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!

More in Training & Fine-tuning

civitai

civitai

14

Training & Fine-tuning

A repository of models, textual inversions, and more

transformerlab-app

transformerlab

24

Training & Fine-tuning

The open source research environment for AI researchers to seamlessly train, evaluate, and

lora-scripts

Akegarasu

36

Training & Fine-tuning

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion

Dreambooth-Stable-Diffusion

XavierXiao

114

Training & Fine-tuning

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion