lllyasviel / lllyasviel/stable-diffusion-webui-forge

RAM leak on starting generation - model double loaded into RAM again on each generation after first

Open
#1,121 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

Clean install.
First generation works fine. When pushing Generate second time - model loaded into RAM again which instantly cause RAM overflow with Flux models.
After generation Forge not unloading models from RAM and its keeps overflowed without reason.
Need add unloading unused models from RAM. Why its not done from beginning? Its just insane that Forge still cannot do that.

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 the issue on a clean install with a Flux model: generate once, then generate again while observing RAM use. Trace the model loading and unloading path for the second generation; done means repeated generations do not load duplicate models or leave RAM continuously consumed.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, performance
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.