Comfy-Org/Qwen-Image-2.1 — new model trending #30 on Hugging Face
Comfy-Org published repackaged Qwen-Image-2.1 weights for ComfyUI, including text-to-image and image-editing workflow templates.
Comfy-Org released repackaged safetensors files of Alibaba's Qwen-Image-2.1 on Hugging Face for use in ComfyUI, trending at #30. The package includes bf16 and int8 diffusion model weights, a Qwen3-VL-8B text encoder in bf16, int8, and w4a8 variants, and a bf16 VAE. Official text-to-image and image-edit workflow templates are provided via GitHub, with installation paths specified for ComfyUI model folders.
- Repackaged Qwen-Image-2.1 diffusion weights in bf16 and int8 for ComfyUI
- Includes Qwen3-VL-8B text encoder variants (bf16, int8, w4a8) and VAE
- Ships with official text-to-image and image-edit workflow templates
Full article60 words · extracted from huggingface.co · click to collapse
# Qwen-Image 2.1
Repackaged model files for ComfyUI.
Original model repository: https://huggingface.co/Qwen/Qwen-Image-2.1
Place the files in the following folders:
```
📂 ComfyUI/
└── 📂 models/
├── 📂 diffusion_models/
│ ├── qwen_image_2.1_bf16.safetensors
│ └── qwen_image_2.1_int8_convrot.safetensors
├── 📂 text_encoders/
│ ├── qwen3vl_8b_bf16.safetensors
│ ├── qwen3vl_8b_int8_convrot.safetensors
│ └── qwen3vl_8b_w4a8.safetensors
└── 📂 vae/
└── qwen_image_2.1_vae_bf16.safetensors
```
Workflow:
- Text-to-image: https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_t2i.json
- Image Edit: https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_image_edit.json
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/Comfy-Org/Qwen-Image-2.1