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

Built with Qwen. Derivative adapters trained by Viggle; converted by T8star.

Modified files:
  qwen_image_2.1_viggle_turbo_v0.2.1_r256_comfy.safetensors
  qwen_image_2.1_viggle_turbo_v0.2.1_r128_comfy.safetensors

Modifications: native ComfyUI tensor keys; independent MLP gate/up adapters
packed into a block-diagonal adapter; explicit alpha matching each rank.
All source adapter values are retained, with zero padding for fused layers.
No base-model weights, training, rank truncation, or weight merging added.
The r128 source was already truncated by Viggle, not by this conversion.

Source: https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo
Revision: b667ee50696e8f4ccd161e02f8af0e43bb5665ed
Upstream notices are retained in NOTICE-UPSTREAM-v0.2.1; license in LICENSE.
Per-file source and conversion checksums are in the manifest JSON files.