Comfy-Org / Comfy-Org/ComfyUI

[Feature Request] Inpaint mask content settings.

Open
#1,972 0 comments 0 reactions 0 assignees View on GitHub
User Support
Dominant language
Python
Stars
133k
Forks
15.7k
Avg merge
1d 10h
Merged PRs (30d)
153

Description

A1111 for example has the option of what content you want to be in the mask when you send it to the sampler when using inpainting:
![image](https://github.com/comfyanonymous/ComfyUI/assets/125952123/0f2357e1-e6c2-4fa9-b13b-444ee918dc03)

It is a very important feature when you try to use inpainting model and set the denoising strength less than 1.0. now if you do that you only get a grey background in the masked area. It is caused by the preprocessing of inpainting VAE encode.
![image](https://github.com/comfyanonymous/ComfyUI/assets/125952123/e1063e0c-816a-4868-8604-fe28d53ef2df)

Some people would say I can use the set_latent_noise_mask node, but I just want to use inpainting model, and set_latent_noise_mask node is not compatible with it. Inpainting model is much better in the consistence between masked area and unmasked area.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.