Qwen Image gguf
by city96
Open source · 57k downloads · 288 likes
3.1
(288 reviews)ImageAPI & LocalAbout
Qwen Image GGUF is an optimized version of the Qwen-Image model, designed to operate efficiently in resource-constrained environments through its conversion to the GGUF format. This model excels in generating and analyzing images, offering advanced capabilities for understanding and producing visual content from text descriptions or prompts. It is particularly well-suited for creative workflows, such as generating artistic images, visual editing, or design assistance, thanks to its seamless integration with tools like ComfyUI. What sets it apart is its ability to maintain remarkable performance even with very low quantizations (such as Q2_K), thanks to a dynamic method that preserves the accuracy of critical layers. Ideal for users seeking a balance between quality, speed, and accessibility, it remains subject to the same restrictions and licenses as the original model.
Documentation
This is a direct GGUF conversion of Qwen/Qwen-Image.
The model files can be used in ComfyUI with the ComfyUI-GGUF custom node. Place the required model(s) in the following folders:
| Type | Name | Location | Download |
|---|---|---|---|
| Main Model | Qwen-Image | ComfyUI/models/diffusion_models | GGUF (this repo) |
| Text Encoder | Qwen2.5-VL-7B | ComfyUI/models/text_encoders | Safetensors / GGUF |
| VAE | Qwen-Image VAE | ComfyUI/models/vae | Safetensors |
Example outputs - sample size of 1, not strictly representative
Notes
[!NOTE] The Q5_K_M, Q4_K_M and most importantly the low bitrate quants (Q3_K_M, Q3_K_S, Q2_K) use a new dynamic logic where the first/last layer is kept in high precision.
For a comparison, see this imgsli page. With this method, even Q2_K remains somewhat usable.
As this is a quantized model not a finetune, all the same restrictions/original license terms still apply.
Capabilities & Tags
gguftext-to-imageenzh
Links & Resources