Text-to-Image
Diffusion Single File
qwen-image
qwen-image-2.1
nvfp4
comfyui
quantized
image-editing
rtx-5090
Instructions to use BennyDaBall/Qwen-Image-2.1-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use BennyDaBall/Qwen-Image-2.1-NVFP4 with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| Built with Qwen | |
| Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved. | |
| BennyDaBall modified the official BF16 image transformer and Qwen3-VL encoder | |
| checkpoints on 2026-09-20 by converting selected linear weights to native NVFP4. | |
| The per-file manifests identify changed tensors and unchanged protected tensors. | |
| The Qwen Image 2.1 VAE is redistributed unchanged. | |
| Source: Comfy-Org/Qwen-Image-2.1 | |
| Revision: ace0edeb3791a594ddfa36ed5f41a178a394e921 | |
| This is an independent conversion, not an official Qwen or Comfy-Org release. | |
| Model use and redistribution remain subject to the included research license. | |