siraxe's picture
Update README.md
af88564 verified
|
Raw History Blame Contribute Delete
1.24 kB
metadata
language:
  - en
tags:
  - minimax-h3 image
  - diffusers
pipeline_tag: image-to-image
base_model: MiniMaxAI/MiniMax-H3-Image
pretty_name: MiniMax-H3-Image experiments
widget:
  - output:
      url: img/6.png
    text: Blend art into the image seamlessly , adjust to match , fill gaps
  - output:
      url: img/5.png
    text: >-
      Blend the object into the image seamlessly , (green cyan rimlight:2.7) top
      lighting,factory building behind , in water , water splashing 
  - output:
      url: img/2.png
    text: Blend the object into the image seamlessly
  - output:
      url: img/4.png
    text: >-
      Blend the object into the image seamlessly , at night , dark night , (cyan
      sky:1.4) , top lighting
  - output:
      url: img/3.png
    text: Blend the object into the image seamlessly , fix perspective
  - output:
      url: img/1.png
    text: change to view selfie shot , keep same identity
Prompt
Blend art into the image seamlessly , adjust to match , fill gaps
Prompt
Blend the object into the image seamlessly , (green cyan rimlight:2.7) top lighting,factory building behind , in water , water splashing
Prompt
Blend the object into the image seamlessly
Prompt
Blend the object into the image seamlessly , at night , dark night , (cyan sky:1.4) , top lighting
Prompt
Blend the object into the image seamlessly , fix perspective
Prompt
change to view selfie shot , keep same identity

H3 Image experiments

1.fusion lineart

2-5.fusion

6.selfie

Fusion loras

v0.1 use at 1.0-1.4

v0.2-v0.3 are stronger , use at 0.4-0.8 for better blending

To use Prompt Weight get https://github.com/kijai/ComfyUI-KJNodes and use MiniMax H3 Prompt Weight node

Trained with https://huggingface.co/ShootTheSound/Fizgig-MiniMax-H3-Image-Training-Adapter