modelscope / modelscope/DiffSynth-Studio

Is there any way to unload a LoRA model?

Open
#820 0 comments 3 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.1k
Forks
1.3k
Avg merge
13h 12m
Merged PRs (30d)
45

Description

I only found "load_lora" from QwenImagePipeline but no "unload". So I just initialize my pipeline when switching to a new LoRA model which takes a lot of time. I'm not sure if there's a function I didn't notice.

It would be highly appreciated if anyone knew the method. Thanks in advance!

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 inspecting QwenImagePipeline and the existing load_lora entry point to understand how LoRA state is attached and replaced. Determine the supported unload or reload behavior, then verify that switching LoRA models avoids reinitializing the pipeline and that the behavior is documented or covered by an appropriate test.

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
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.