AI换衣模型Utopian_pony_inpainting Stable Diffusion model

此模型是用于逼真图像的修复模型。
-使用此模型，您可以更改或删除生成图像的衣服。

This model is an inpaint model for realistic images.

-With this model you can change or remove the clothes of the generated images.

Improve the quality of your inpainting with the rich knowledge of pony models and the flexibility of prompts to meet the needs of more creative purposes.

 

-Uploaded v2 version

I chose v2 between 4 prototypes, each has its pros and cons. If you want to try the test version, I will upload.

 

How to use:

Soft inpainting check

Sampler Euler a

Schedule type uniform

Mask bluer 4~8

CFG Scale 3~6

Denoising strength 0.9

-Soft inpainting setting

change “Transition contrast boost” to 1 (default 4)

change “Difference threshold” to 0.1~0.25 (default 0.5)

Tips:

• Only masked is always best for quality.
• Start with Masked content “original”, if not worked change to “latent noise” or “fill”.
• Use image size with height + width>2000~2500 (Recommended size for SDXL).

  or use resized by scale around recommended size (aspect-ratio-helper).

• You can change the pose and situation by painting masks more creative.
• Using normal model for refiner (eg. pony realism) at 0.8~0.9 can produce great results.

  especially when you have made significant changes to your image.

• If you mask a small part, it is a good idea to mask the top and bottom of the image so that the model can see whole picture.

 

Your mask and image works as quality prompt, You don’t need a lot of prompts, keep them to a minimum and let the model do work.

woman, maid_costume

If your subject is in a specific pose, provide prompts to help them.

woman, lying on stomach, from side

If you want to change the pose or situation, mask the area where it should be written when that situation occurs.

woman, spread legs

 

-Use this model only for AI-generated images.

-Prohibits uses that harm any person by using this model on real-world images.