nunchaku-qwen-image-edit

This repository contains Nunchaku-quantized versions of [Qwen-Image-Edit](https://huggingface.co/Qwen/Qwen-Image-Edit), an image-editing model based on [Qwen-Image](https://huggingface.co/Qwen/Qwen-Image), advances in complex text rendering. It is optimized for efficient inference while maintaining minimal loss in performance. No recent news. Stay tuned for updates! - **Developed by:** Nunchaku Team - **Model type:** image-to-image - **License:** apache-2.0 - **Quantized from model:** [Qwen-Image-Edit](https://huggingface.co/Qwen/Qwen-Image-Edit) **Data Type**: `INT4` for non-Blackwell GPUs (pre-50-series), `NVFP4` for Blackwell GPUs (50-series). **Rank**: `r32` for faster inference, `r128` for better quality but slower inference. Standard inference speed models for general use 4-step distilled models fused with [Qwen-Image-Edit-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-Lightning-4steps-V1.0-bf16.safetensors) using LoRA strength = 1.0 8-step distilled models fused with [Qwen-Image-Edit-Lightning-8steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Edit-Lightning-8steps-V1.0-bf16.safetensors) using LoRA strength = 1.0 - **Inference Engine:** [nunchaku](https://github.com/nunchaku-tech/nunchaku) - **Quantization Library:** [deepcompressor](https://github.com/nunchaku-tech/deepcompressor) - **Paper:** [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](http://arxiv.org/abs/2411.05007) - **Demo:** [demo.nunchaku.tech](https://demo.nunchaku.tech) - Diffusers Usage: See [qwen-image-edit.py](https://github.com/nunchaku-tech/nunchaku/blob/main/examples/v1/qwen-image-edit.py) and [qwen-image-edit-lightning.py](https://github.com/nunchaku-tech/nunchaku/blob/main/examples/v1/qwen-image-edit-lightning.py). Check this [tutorial](https://nunchaku.tech/docs/nunchaku/usage/qwen-image-edit.html) for more advanced usage. - ComfyUI Usage: See [nunchaku-qwen-image-edit.json](https://nunchaku.tech/docs/ComfyUI-nunchaku/workflows/qwenimage.html#nunchaku-qwen-image-edit-json). @inproceedings{ li2024svdquant, title={SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models}, author={Li*, Muyang and Lin*, Yujun and Zhang*, Zhekai and Cai, Tianle and Li, Xiuyu and Guo, Junxian and Xie, Enze and Meng, Chenlin and Zhu, Jun-Yan and Han, Song}, booktitle={The Thirteenth International Conference on Learning Representations}, year={2025} }