Comfy-Org / Comfy-Org/ComfyUI

Experiencing VRAM OOM (Out of Memory) issues with the same workflow after upgrading to ComfyUI 0.27. Rolling back to 0.22 fixes it. Any solutions or workarounds?

Open
#14,789 10 comments 0 reactions 0 assignees View on GitHub
Potential Bug
Dominant language
Python
Stars
133k
Forks
15.7k
Avg merge
1d 7h
Merged PRs (30d)
158

Description

### Custom Node Testing

- [ ] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

Experiencing VRAM OOM (Out of Memory) issues with the same workflow after upgrading to ComfyUI 0.27. Rolling back to 0.22 fixes it. Any solutions or workarounds?

### Actual Behavior

Experiencing VRAM OOM (Out of Memory) issues with the same workflow after upgrading to ComfyUI 0.27. Rolling back to 0.22 fixes it. Any solutions or workarounds?

### Steps to Reproduce

Experiencing VRAM OOM (Out of Memory) issues with the same workflow after upgrading to ComfyUI 0.27. Rolling back to 0.22 fixes it. Any solutions or workarounds?

### Debug Logs

```powershell
Experiencing VRAM OOM (Out of Memory) issues with the same workflow after upgrading to ComfyUI 0.27. Rolling back to 0.22 fixes it. Any solutions or workarounds?
```

### Other

Experiencing VRAM OOM (Out of Memory) issues with the same workflow after upgrading to ComfyUI 0.27. Rolling back to 0.22 fixes it. Any solutions or workarounds?

Contributor guide

Open the contributing guide

Research direction

Start by reviewing the issue report and its discussion for details about the workflow, hardware, and any findings from the upgrade comparison; the report does not name relevant files or tests. Reproduce the VRAM out-of-memory behavior on version 0.27 and compare it with 0.22 to identify what changed. Done means locating a cause and confirming a fix or workaround resolves the reported failure.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.