metadata
tags:
- text-to-image
- lora
- qwen
- qwen image
- QIE
- lightning
- lightx2v
widget:
- output:
url: images/ComfyUI_04979_.png
text: >-
head_swap: start with Picture 1 as the base image, keeping its lighting,
environment, and background. remove the head from Picture 1 completely and
replace it with the head from Picture 2, strictly preserving the hair, eye
color, nose structure of Picture 2. copy the direction of the eye, head
rotation, micro expressions from Picture 1, high quality, sharp details,
4k
parameters:
negative_prompt: >-
bad quality, noise, blurry, worst quality, low resolution, blur,
distortion, unnatural blending, cartoon, illustration, painting
base_model: Qwen/Qwen-Image-Edit-2511
instance_prompt: null
library_name: diffusers
CustomLightning
- Prompt
- head_swap: start with Picture 1 as the base image, keeping its lighting, environment, and background. remove the head from Picture 1 completely and replace it with the head from Picture 2, strictly preserving the hair, eye color, nose structure of Picture 2. copy the direction of the eye, head rotation, micro expressions from Picture 1, high quality, sharp details, 4k
- Negative Prompt
- bad quality, noise, blurry, worst quality, low resolution, blur, distortion, unnatural blending, cartoon, illustration, painting
Model description
These models are merges and extractions of LoRa's that I made for my personal use and to try to correct some oversaturation and plastic skin issues generated by the Lightning LoRa's Lightning LoRa's from Lightx2v.
Download model
Download them in the Files & versions tab.