nextcloud / nextcloud/text2image_stablediffusion2

Unload model when not needed

Open
#7 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
Python
Stars
1
Forks
1
PR merge metrics
No merged PRs in 30d

Description

How to use GitHub

Feature request

**Which Nextcloud Version are you currently using: 30.0.6

Is your feature request related to a problem? Please describe.
my problem is that I have only 1 GPU in my server with 24 GB vRAM. Stable diffusion alone reserver abour 17 GB of RAM so for my other models I only have 7 GB left.

Describe the solution you'd like
Ollama for example unloads models that are not needed at the moment. This would be awesome so the models that I want to use have enough vRAM left. (Context Chat and Chat with AI)

Additional context
Here is a screenshot of nvbidia smi when stable difision and context chat is running

Image

When I not try to use llama3.3 it is super slow or cant even start because I habe not enough vRAM

Contributor guide

Open the contributing guide

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

No files, tests, or entry points are identified in the issue. First inspect the repository to find how Stable Diffusion and other models are loaded and retained, then define and test unloading behavior that frees enough VRAM for another model to start.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.