https://huggingface.co/lightx2v/Qwen-Image-Lightning/tree/main

https://huggingface.co/QuantStack/Qwen-Image-Distill-GGUF/tree/main

gguf + the lightning lora at 8 steps works, using this workflow:

https://huggingface.co/datasets/theaidealab/workflows/blob/main/qwen_image_distill_gguf.json

Q5 gguf. now I wanna see if Q8 works fine with multigpu. what is default qwen image size btw?