Qwen Image 2.1 GGUF

Qwen Image 2.1 is a diffusion transformer for text-to-image generation and image editing. It uses the Qwen3-VL 8B text encoder and supports image references through ComfyUI.

Upstream model repositoryQwen-Image-2.1 GGUF on Hugging Face

The GGUF files below are local builds. They are ready for the Qwen Image 2.1 support in ComfyUI and ComfyUI-GGUF.

Example

Prompt: 35mm film grain, dreamlike levitation, soft vintage color palette, minimalist expansive composition, sun-drenched golden hour, candid cinematic realism, low-angle perspective, a 25 years old french woman with bob haircut and thin body is jumping in the air. there is a speech bubble saying 'Qwen Image 2.1 GGUF' with bold letters

Available Quantizations

Quant	File
Q4_0	qwen_image_2.1_Q4.gguf
Q8	qwen_image_2.1_Q8.gguf
Q8_CR	qwen_image_2.1_Q8_CR.gguf
Q4_CR	Work in progress

The standard Q4_0 and Q8 files use GGML quantization. Q8_CR uses the native INT8 ConvRot path.

Model Input and Output

Inputs

Input	Description
Text prompt	A text description for image generation or editing instructions.
Reference image	Optional image input for image editing and visual conditioning.

Outputs

Image, RGBA (Supports transparent background)

ComfyUI Setup

Load the model with the GGUF loader node from comfyui-gguf-reboot. Use the Qwen Image 2.1 workflow supplied by the installed ComfyUI version.

Dependencies

Place the matching files from the upstream Qwen Image 2.1 release in the ComfyUI model folders.

Component	Folder
Qwen Image 2.1 GGUF	models/diffusion_models/ or models/unet/
Qwen3-VL 8B text encoder	models/clip/ or text_encoders/
Qwen Image VAE	models/vae/

Workflow downloads

Import these JSON files into ComfyUI.

JSON fileText-to-Image workflowJSON fileImage Edit workflow