lllyasviel / lllyasviel/stable-diffusion-webui-forge

[Bug]: Loading SDXL model crashes unexpectedly.

Open
#549 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

### Checklist

- [ ] The issue exists after disabling all extensions
- [ ] The issue exists on a clean installation of webui
- [ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
- [X] The issue exists in the current version of the webui
- [X] The issue has not been reported before recently
- [ ] The issue has been reported before but has not been fixed yet

### What happened?

I am using the --always-cpu flag to run exclusively on the CPU, however, upon attempting to load the SDXL model, it crashes instantly (owing to inadequate available RAM—having only 12GB in total, the system has to rely on virtual memory swapping, which is the fundamental reason for the crash). In the original web UI, the SDXL model loads properly and generates images without any problems.

### Steps to reproduce the problem

None

### What should have happened?

None

### What browsers do you use to access the UI ?

_No response_

### Sysinfo

None

### Console logs

```Shell
Loading weights [8421598e93] from E:\StableDiffusionForge\models\Stable-diffusion\AnythingXL_xl.safetensors
请按任意键继续. . .
```

### Additional information

_No response_

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 SDXL model loading with --always-cpu and the AnythingXL_xl.safetensors model referenced in the report. Inspect the loading path reached before the console stops and compare behavior with the original web UI. Done means the model loads without crashing on the reported CPU and memory setup, or the failure is narrowed to a documented limitation.

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
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.