README.md

metadata

license: apache-2.0
base_model:
  - Qwen/Qwen-Image-Edit-2509
pipeline_tag: image-to-image
widget:
  - text: use image 2 as background for image 1 fairy
    output:
      url: workflow-demo2.png
  - text: use image 2 city night view as background for image 1
    output:
      url: workflow-demo.png

qwen-image-edit-plus-gguf

• use 8-step (lite-lora auto applied); save up to 70% loading time
• run it with gguf-connector; simply execute the command below in console/terminal

ggc q7

GGUF file(s) available. Select which one to use:

1. qwen-image-edit-plus-iq4_nl.gguf
2. qwen-image-edit-plus-q2_k.gguf
3. qwen-image-edit-plus-q8_0.gguf

Enter your choice (1 to 3): _

• opt a gguf file in your current directory to interact with; nothing else

run it with gguf-node via comfyui

• drag qwen-image-edit-plus to > ./ComfyUI/models/diffusion_models
• *anyone below, drag it to > ./ComfyUI/models/text_encoders
  • option 1: just qwen2.5-vl-7b-test [5.03GB]
  • option 2: just qwen2.5-vl-7b-edit [7.95GB]
  • option 3: both qwen2.5-vl-7b [4.43GB] and mmproj-clip [608MB]
• drag pig [254MB] to > ./ComfyUI/models/vae

Prompt

apply the image 2 full costume to image 1 singing girl

Prompt

use image 2 city night view as background for image 1

Prompt

use image 2 as background for image 1 fairy

run it with diffusers

• might need the most updated git version for QwenImageEditPlusPipeline and i quant support, should after this commit; install the updated git version diffusers by:

pip install git+https://github.com/huggingface/diffusers.git

• simply replace QwenImageEditPipeline by QwenImageEditPlusPipeline for the qwen-image-edit inference (see here)
• for multiple image input, please refer to the inference example from base model

reference

• gguf-node (pypi|repo|pack)
• gguf-connector (pypi)