lllyasviel / lllyasviel/stable-diffusion-webui-forge

System Ram only increases on model swap

Open
#2,566 3 comments 1 reaction 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'm on Pop!_OS using 32 GB ram and I have a 3090ti

I'm using Illustrious Checkpoints and loras. When switching checkpoints or loras system ram usage only increases.

Funny enough, going to Settings / Other / Actions
and hitting the "unload all models" button actually increases system ram usage as well!

I like to test different styles and this has me swapping models a lot causing my system to crash over time.

I tried the -xformers --cuda-malloc args as well... ya that didn't fix anything.

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 reproducing repeated checkpoint and LoRA swaps on Pop!_OS, then use Settings / Other / Actions to test whether “unload all models” also increases system RAM. Track system memory across swaps and unloads; done means repeated model changes no longer cause ongoing RAM growth or eventual crashes.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
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.