Image Generation AI with ComfyUI: Inpaint Edition

Progress 10 / 15
Table of Contents

If using Inpaint of StableDiffusion, you can modify specific part of image or add new element. In this article, I explain specific procedure to perform Inpaint with StableDiffusion using ComfyUI.

Work Flow

1. Introduction of ComfyUI

Please refer to this article.

【Stable Diffusion】ComfyUIを使って画像生成AIで遊んでみよう【導入編】

>-

blog.otama-playground.com

2. Creation of Workflow

Yellow is added node.

Workflow
Workflow

Referencing below. https://comfyanonymous.github.io/ComfyUI_examples/inpaint/

3. Creation of mask

  1. Right click Load Image and select item called Open in Mask Editor
  2. Paint part you want to Mask black.
  3. Click Save to node and complete
Option appearing by right click
Option appearing by right click
After Mask
After Mask

Note: Initial Mi〇ey had art style not matching and didn’t go well so I gave up

4. Generate

Write what you want to generate in masked part in prompt and generate.

Generation Result

Masked only sky of famous xp wallpaper

Mask Image
Mask Image

Prompt

apocalyptic scene, meteors falling, stars, colonies, numerous explosions, intense fire, smoke, numerous meteors, dramatic sky, destruction, detailed environment, high-quality, 4K, dynamic lighting, realistic textures, dark atmosphere, cinematic, depth of field, chaos, ruins, concept art, artstation, vibrant colors, embedding:DarkFantasy,

Generated Image
Generated Image

Image with apocalyptic feeling was generated nicely.

Conclusion

This time, I explained method to perform Inpaint using StableDiffusion. By mastering Inpaint technology, masking specific part and adding new element becomes possible, enabling diverse expression. I am happy if this article becomes reference for image editing using StableDiffusion.

If you want to try other techniques related to image generation, please utilize the link collection below.

Stable Diffusionガイド:画像生成に役立つリンク集

>-

blog.otama-playground.com