Qwen Image 2.1 GGUF Conversion.

Loader nodes: https://github.com/molbal/ComfyUI-GGUF / https://registry.comfy.org/publishers/molbal/nodes/comfyui-gguf-reboot

Workflow settings

Sampler settings

Both templates sample with steps 25, cfg 1, the euler sampler, and the simple scheduler. The text to image workflow keeps the seed fixed, and the image edit workflow randomizes it.​

Resolution

Text to image: the Resolution Selector node sets the aspect ratio (1:1, 16:9, 9:16, 3:2, 2:3, 4:3, 3:4, 21:9) and a megapixel target, where 1.0 MP is about 1024x1024. The template defaults to 1:1 at 1 MP. Qwen-Image-2.1 generates natively at 2K, so set the target to about 4.0 MP for a 2048x2048 square output.

Image edit: with custom_size off, which is the template default, the output follows image_1’s aspect ratio, scaled to about resolution x resolution pixels (default 1024, rounded to multiples of 32). That is not the original pixel size of image_1. Set resolution to 0 to keep each reference image at its own size, rounded to a multiple of 32. Turn custom_size on to use the Resolution Selector canvas instead, and keep it close to the resized image_1 size, otherwise the edit can shift.​

Prompting for image edit

Reference images are spliced into the text encoder in slot order, and the prompt addresses each one by index. The template prompt is a good example of the pattern:

Keep the character and pose in <image1> unchanged, put this light