Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved.

Built with Qwen.

This repository redistributes a modified version of the LoRA adapter from Viggle/Qwen-Image-2.1-viggle-turbo:
https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo

Viggle trained and released the 4-step distilled Qwen-Image-2.1 LoRA. T8star converted its Diffusers tensor keys to native ComfyUI Qwen Image 2.1 model paths and renamed the output file. The BF16 tensor payload was copied byte for byte; no additional training or weight changes were made. The converted LoRA is separate from Viggle's full fine-tuned transformer.

Original LoRA SHA256: 5c494dce662a95898d0988831af733b203ceced9116a82aa099c997f96ea1a3a
Converted LoRA SHA256: 92be516174803a279b6a590fd3861a188c89ed16ebc419daf97b982f0afe53c1

The model is subject to the Qwen RESEARCH LICENSE AGREEMENT distributed alongside this notice as LICENSE. Use is limited to non-commercial research or evaluation. Commercial use requires a separate license from the licensor.