---
license: other
license_name: qwen-research
license_link: https://huggingface.co/Qwen/Qwen-Image-2.1/blob/main/LICENSE
tags:
- comfyui
- diffusion-single-file
base_model:
- Qwen/Qwen-Image-2.1
---

# Qwen-Image 2.1

Repackaged model files for ComfyUI, with INT4 ConvRot converted for testing in Radiant Canvas for fast macOS inference (https://apps.apple.com/us/app/radiant-canvas-ai-image-gen/id6802973075)

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_int4_convrot.safetensors
    │   └── qwen_image_2.1_int8_convrot.safetensors
    ├── 📂 text_encoders/
    │   ├── qwen3vl_8b_bf16.safetensors
    │   ├── qwen3vl_8b_int4_convrot.safetensors
    │   ├── qwen3vl_8b_int8_convrot.safetensors
    │   └── qwen3vl_8b_w4a8.safetensors
    └── 📂 vae/
        └── qwen_image_2.1_vae_bf16.safetensors
```

The INT4 ConvRot files use ComfyUI's native ConvRot W4A4 format. Use a recent
ComfyUI build and load them with the standard diffusion model and text encoder
loaders.