lllyasviel / lllyasviel/stable-diffusion-webui-forge

Found a commit that removes one of the most advanced upscalers, LDSR, why did this happen?

Open
#1,798 4 comments 5 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

I found that the most powerful option, **LDSR**, disappeared from the list of upscalers. I dug through the commits for a long time and found that there were three commits that completely cut out such a powerful tool. I can't understand why this was done and how to get it back?

Here are the culprits of the problem: https://github.com/lllyasviel/stable-diffusion-webui-forge/commit/471d07caddb423d74fdaa5f04f6f71eb313c65f2 and https://github.com/lllyasviel/stable-diffusion-webui-forge/commit/bccf9fb23a2cbc9d42091a856b3d35b2c4414d51 and more mini fix.

From the commit, all I understood was that perhaps this upscaler was unsafe and closed, but there is little description, so I don’t understand this commit. Can you describe what problems it caused?

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 reading commits 471d07caddb423d74fdaa5f04f6f71eb313c65f2 and bccf9fb23a2cbc9d42091a856b3d35b2c4414d51, then trace the LDSR upscaler history in the repository. Document the specific problems that led to its removal and whether a safe restoration path exists; completion requires a clear explanation rather than an assumed code change.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.