NOTICE
======

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-Image-2.1 (https://huggingface.co/Qwen/Qwen-Image-2.1,
revision 790c92633540aa0cb11d9abf19eb46d861714758). It merges two derivative works of it into the base pipeline:

  Viggle/Qwen-Image-2.1-viggle-turbo (v0.2.1)    revision bb26a0f38e5fe6c124aaccc9187a87eed5d9ed13
  madebyollin/texture-fix-vae-for-qwen-image-2.1 revision e9f84623d22c47f8bc9fb799bc54201fa53cf80b

The full agreement is in `LICENSE`, a copy of it is given to every recipient of these files.

Modified files, as required by section 2.b of the agreement:

  transformer/*.safetensors  the Qwen-Image-2.1 DiT with the Viggle turbo v0.2.1 LoRA (rank 256,
                             alpha 256, F32 factors from `peft_v0.2.1/`) merged into the 227
                             projection weights it targets; the sum is computed in fp32 and stored
                             in fp16. Every other tensor is the upstream bf16 value stored in fp16.
  vae/                       the Texture-Fix VAE by madebyollin (decoder fine-tune of the
                             Qwen-Image-2.1 VAE, encoder unchanged), fp32, byte-identical to its source
  scheduler/                 the Viggle turbo scheduler config (`shift_terminal` null instead of 0.02)

Unchanged from Qwen/Qwen-Image-2.1: text_encoder/, processor/, transformer/config.json,
model_index.json, LICENSE. Files added by this repository: README.md, media/.

Built with Qwen.


Upstream notices
================

--- Viggle/Qwen-Image-2.1-viggle-turbo ---
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     Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r256.safetensors - v0.2.1: a distilled LoRA adapter (rank 256, alpha 256) for the base transformer, sampled in 6 steps, stored bf16
  ADDED     peft_v0.2.1/ - the same v0.2.1 adapter in peft key format, F32 as trained
  ADDED     Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r128.safetensors - the v0.2.1 adapter truncated to rank 128 (alpha 128) by per-layer SVD, stored bf16
  ADDED     comfyui/ - ComfyUI custom nodes (viggle_turbo.py) and text-to-image / edit workflows, and the edit workflow's two example input photos (comfyui/input/); no model weights
  ADDED     Qwen-Image-2.1-viggle-turbo-v0.2-5step-lora-r256.safetensors - v0.2: the previous distilled LoRA adapter (rank 256, alpha 256), sampled in 5 or 6 steps, stored bf16
  ADDED     peft_v0.2/ - the same v0.2 adapter in peft key format, F32 as trained
  ADDED     Qwen-Image-2.1-viggle-turbo-v0.2-5step-lora-r128.safetensors - the v0.2 adapter truncated to rank 128 (alpha 128) by per-layer SVD, stored bf16
  ADDED     Qwen-Image-2.1-viggle-turbo-4step-lora-r64.safetensors - v0.1: a 4-step distilled LoRA adapter (rank 64, alpha 64), stored bf16
  ADDED     peft/ - the same v0.1 adapter in peft key format, F32 as trained
  MODIFIED  transformer/ - v0.1: the base transformer after a full-parameter 4-step distillation fine-tune, stored bf16
  MODIFIED  scheduler/scheduler_config.json - the base scheduler config with shift_terminal changed from 0.02 to null

No other file of the base model is copied or modified; processor/, text_encoder/ and vae/ are loaded from
Qwen/Qwen-Image-2.1 at runtime.

Source checkpoints: v0.2.1 LoRA - run v6_isg, step 700 (EMA student); v0.2 LoRA - run v6_isg, step 600 (EMA student); v0.1 transformer/ - run v4_anchor, step 400 (EMA student, full fine-tune); v0.1 LoRA - run v2_16gpu, step 400 (EMA student)

--- madebyollin/texture-fix-vae-for-qwen-image-2.1 ---
Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved.

Modified files: diffusion_pytorch_model.safetensors and texture_fix_vae_for_qwen_image_2.1_bf16.safetensors contain the
Qwen-Image-2.1 VAE (https://huggingface.co/Qwen/Qwen-Image-2.1) with modified (finetuned) decoder weights.
The modifications were made by madebyollin in 2026. The encoder weights are unchanged.