calcuis/qwen-image-edit-gguf

qwen-image-edit-gguf

• drag qwen-image-edit to > ./ComfyUI/models/diffusion_models
• either 1 or 2 below, drag it to > ./ComfyUI/models/text_encoders
  • option 1: qwen2.5-vl-7b-edit [7.95GB] (recommended)
  • option 2: both qwen2.5-vl-7b [4.43GB] and mmproj-clip [1.35GB]
• drag pig [254MB] to > ./ComfyUI/models/vae

note: option 1 (pig quant) is recommended since just one file and less chance for oom; option 2 (llama.cpp quant) is also fine if you have good machine/gpu and make sure both the text model and mmproj (vision clip) are prepared

Prompt

Remove all UI text elements from the image. Keep the feeling that the characters and scene are in water. Also, remove the green UI elements at the bottom.

Prompt

put a hat to the cat