yycc's picture
Add --turbo: 2 LoRA steps + 6 Qwen-Image-2.1-Turbo steps
21d9a3e verified
Raw History Blame Contribute Delete
739 Bytes
Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved.
This repository is a derivative work of Qwen/Qwen-Image-2.1, produced by Viggle.
Built with Qwen.
It contains:
ADDED viggle-image-swap-v0.1-lora.safetensors - a LoRA adapter (rank 256, alpha 256) for the base transformer, stored bf16
ADDED inference/swap.py - inference code (Apache License 2.0, see LICENSE-CODE); it loads Qwen/Qwen-Image-2.1 at runtime,
and Qwen/Qwen-Image-2.1-Turbo too with --turbo
No file of the base models is copied or modified; every component of Qwen/Qwen-Image-2.1 and Qwen/Qwen-Image-2.1-Turbo is
loaded from its repository at runtime.