Frank
02883d3ed2
Copy of the legacy ~/.pi/agent/docs tree rebuilt as the command-center knowledge base: concept files promoted to path identity, index listings stripped of frontmatter, all wikilinks/relative links resolved, every checkable claim verified against the live fleet (Dankserver = Ryzen 7 7700X + RTX 3090; Strix Halo is Dankclaw), unverifiable claims tagged. kb-lint exits 0.
115 lines
3.1 KiB
Markdown
115 lines
3.1 KiB
Markdown
---
|
|
type: reference
|
|
title: ComfyUI Troubleshooting
|
|
description: Common errors, diagnostics, and recovery steps for ComfyUI on dankclaw.
|
|
tags:
|
|
- image-generation
|
|
- comfyui
|
|
- troubleshooting
|
|
- dankclaw
|
|
- unverified
|
|
verified: 2026-08-28
|
|
---
|
|
|
|
# ComfyUI Troubleshooting
|
|
|
|
Procedures for diagnosing and fixing ComfyUI on dankclaw.
|
|
|
|
## Service Will Not Start
|
|
|
|
Check the journal logs first.
|
|
|
|
```bash
|
|
ssh dank@dankclaw 'journalctl --user -u comfyui --no-pager -n 100'
|
|
```
|
|
|
|
### "RuntimeError: No HIP GPUs are available"
|
|
|
|
Cause: The container's ROCm PyTorch cannot see the Strix Halo (gfx1151) GPU. This can happen when `/dev/kfd` and `/dev/dri` are not properly passthrough, or when the ROCm PyTorch build doesn't match the GPU architecture.
|
|
|
|
Fix: Verify GPU passthrough is configured in `compose.yaml` (should include `/dev/kfd` and `/dev/dri`). The container image is `comfyui-rocm:gfx1151` which should contain the correct ROCm kernels.
|
|
|
|
Check that the container image uses the AMD gfx1151 base:
|
|
|
|
```bash
|
|
ssh dank@dankclaw 'podman inspect comfyui --format "{{.Config.Image}}"'
|
|
```
|
|
|
|
If the GPU still doesn't work, ensure the host user is in the `render` group:
|
|
|
|
```bash
|
|
ssh dank@dankclaw 'id dank'
|
|
```
|
|
|
|
### "HIP error: invalid device function"
|
|
|
|
Cause: The ROCm PyTorch kernels don't match the GPU architecture. The ComfyUI container uses the AMD gfx1151 base image (`comfyui-rocm:gfx1151`), but if PyTorch was reinstalled without the ROCm build, this error occurs.
|
|
|
|
Fix: Reinstall the gfx1151 ROCm PyTorch. The container image already ships the correct version (torch 2.9.1+rocm). If the venv was rebuilt outside the container, reinstall:
|
|
|
|
```bash
|
|
ssh dank@dankclaw 'cd ~/ComfyUI && source venv/bin/activate && \
|
|
pip uninstall torch torchvision torchaudio pytorch-triton-rocm -y && \
|
|
pip install torch torchvision torchaudio'
|
|
```
|
|
|
|
### Port 8188 Already in Use
|
|
|
|
```bash
|
|
ssh dank@dankclaw 'ss -tlnp | grep 8188'
|
|
```
|
|
|
|
Kill the conflicting process or change the port in the service file.
|
|
|
|
## Model Not Loading
|
|
|
|
Check that the model file exists in the correct path.
|
|
|
|
```bash
|
|
ssh dank@dankclaw 'ls -lh ~/models/checkpoints/*.safetensors'
|
|
```
|
|
|
|
Verify `extra_model_paths.yaml` points to the correct base path.
|
|
|
|
```bash
|
|
ssh dank@dankclaw 'cat ~/ComfyUI/extra_model_paths.yaml'
|
|
```
|
|
|
|
Restart ComfyUI after adding or removing models.
|
|
|
|
```bash
|
|
ssh dank@dankclaw 'systemctl --user restart comfyui'
|
|
```
|
|
|
|
## Cannot Reach the Web UI
|
|
|
|
Test connectivity from dankware.
|
|
|
|
```bash
|
|
curl -s -o /dev/null -w "%{http_code}" http://dankclaw:8188
|
|
```
|
|
|
|
Expected response: `200`.
|
|
|
|
If the response is empty or times out, verify the service is running.
|
|
|
|
```bash
|
|
ssh dank@dankclaw 'systemctl --user status comfyui --no-pager'
|
|
ssh dank@dankclaw 'ss -tlnp | grep 8188'
|
|
```
|
|
|
|
## Out of Memory
|
|
|
|
ComfyUI loads the full model into RAM. FLUX.2 klein 4B requires approximately 13 GB. The system has 119 GB total. Close other memory-intensive applications if OOM occurs.
|
|
|
|
Check memory usage.
|
|
|
|
```bash
|
|
ssh dank@dankclaw 'free -h'
|
|
ssh dank@dankclaw 'systemctl --user show comfyui --property=MemoryCurrent'
|
|
```
|
|
|
|
## See Also
|
|
|
|
- [comfyui](index.md) — Main documentation
|