lllyasviel / lllyasviel/sd-forge-layerdiffuse

希望能兼容controlnet的tile预处理器。I hope to be compatible with the "tile" preprocessor function of "controlnet".

Open
#93 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
4.1k
Forks
352
PR merge metrics
No merged PRs in 30d

Description

我希望可以兼容“controlnet”的“tile”预处理器功能,现在“layer diffusion”只兼容“controlnet”的“Lineart”预处理器,却没有办法精确控制图片各个区域的颜色,对于颜色的控制纯粹只依靠提示词,但是单纯的提示词控制非常不稳定,如果可以的话,我希望还是兼容一下“controlnet”的“tile”预处理器功能。
I hope to be compatible with the "tile" preprocessor function of "controlnet". Currently, "layer diffusion" is only compatible with the "Lineart" preprocessor of "controlnet", but it cannot precisely control the colors of various areas of the image. Color control only relies on prompt words, but simple prompt word control is very unstable. If possible, I hope to be compatible with the "tile" preprocessor function of "controlnet".
![QQ截图20240414092257](https://github.com/layerdiffusion/sd-forge-layerdiffuse/assets/166965276/a4cf7f59-7f90-47f2-936a-79a96e4b2d09)

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

Start by tracing the existing ControlNet Lineart compatibility path in the layer diffusion integration, then compare the requirements of ControlNet's tile preprocessor. The work is done when tile preprocessing is supported and can provide more reliable color control across image regions; confirm behavior with the project's existing checks for the Lineart path.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
28/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.