Basic workflow for Qwn-Image-Edit Lightning 4steps. It can also be used for FP8, (CFG 2.5 - steps 20) just load the diffusion model and text encoder. Remember that the Qwen-Image model, especially in GGUF cases, behaves differently from the prompt if the size of the image is not supported by the model.
928x1664, 1056x1584, 1140x1472, 1328x1328, 1664x928, 1584x1056, 1472x1140

Error: Can't find mmproj file for 'Qwen2.5-VL-7B-Instruct-Q3_K_M.gguf' (matching:'qwen2.5-vl-7b-instruct')! Qwen-Image-Edit will be broken

https://civarchive.com/models/1881174?modelVersionId=2145487

v1.1

Minor changes for convenience: added FP8 nodes and the ability to resize images based on Qwen Image, SDXL, and Flux-supported image sizes.