Bedovyy

/

Qwen-Image-Edit-2511-NVFP4

like 32

It is actually nvfp4/fp8/bf16 mixed model, refered from https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/diffusion_models
even though the size of model is similar to fp8, generation speed is much faster.