lllyasviel / lllyasviel/stable-diffusion-webui-forge

problem with controlnet depth in inpaint upload

Open
#1,140 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

forge does not generate images well with controlnet depth compared to a1111

the parameters and model are exactly the same

i use depth midas with diffusers_xl_depth_full [2f51180b]
the model is creapromptLightning_creapromptHyperCFGV2

original image
https://imgur.com/a/yAmSgQ4

forge image
https://imgur.com/a/i0DMaXr

image of a1111
https://imgur.com/a/NqmED5O

in img2img, there is no problem, only inpaint upload, with a mask

thanks

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No file or test is named. First reproduce the difference using ControlNet depth with depth midas, diffusers_xl_depth_full [2f51180b], and creapromptLightning_creapromptHyperCFGV2, comparing inpaint upload with a mask against img2img and A1111; done means the inpaint result no longer shows the reported discrepancy under the same parameters.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.