My TG Channel - https://t.me/StefanFalkokAI
My TG Chat - https://t.me/+y4R5JybDZcFjMjFi
Hi! I introduce my working workflows with Qwen Image 2512 generating image for ComfyUI.
I have included workflow with Qwen Image models
You need to have Qwen Image Model (https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/diffusion_models), clip (https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/text_encoders) and vae (https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae)
GGUF Qwen Image 2512- https://huggingface.co/unsloth/Qwen-Image-2512-GGUF/tree/main
If you need 4steps and 8steps loras for Qwen Image - https://huggingface.co/lightx2v/Qwen-Image-Lightning/tree/main
Also 4steps and 8steps lora from https://civarchive.com/models/2046883?modelVersionId=2318885
download my ComfyUI Build https://huggingface.co/datasets/StefanFalkok/ComfyUI_portable_torch_2.10.0_cu130_cp313_sageattention_triton/tree/main, also u need download and install CUDA 13.0 (https://developer.nvidia.com/cuda-13-0-0-download-archive) and VS Code (https://visualstudio.microsoft.com/downloads/)
Leave comments if you have trouble or you found the problem with workflows
Description
FAQ
Comments (5)
When using Sageattention, with --use-sage-attention --fast when starting run_nvidia_gpu.bat, I got an error that outputted a black image. according to my ddocj, the Qwen model does not support Sageattention, right?
then turn off sageattention and generate qwen images without sageattention
you need a node called "Patch Sage Attention KJ" with sageattn_qk_int8_pvfp16_cuda between the model and the ksampler
@cmansom600 Thanks, I no longer have to edit the .bat file, restart comfy every time I use Qwen.
@cmansom600 sage doesn't work with qwen, at all. only flash_attn does