Frank
689228e60d
Second half of the purge (the first covered the persona, AGENTS.md, README.md, and the distillation of the per-host pages). Every remaining identifier is gone: hostname, both LAN addresses, and the Wi-Fi SSID. 34 count-checked substitutions across 22 files — indexes, tool/research pages, the inventory census, the changelog, one generated HTML report, and five managed skills. Facts kept, names dropped: a history entry keeps its four-page listing as a nameless summary, the syslog excerpts keep every timestamp and line, and the census keeps the .zcompdump rows (the zsh version stamps are the useful part, the hostname was not). Deliberately unchanged: install.sh's --host case list and the packages/<hostname>.pkgs filename, where the hostname is the lookup key. Left out of scope by Frank's call: agent/memories/** — past-session records the learn pipeline rewrites. kb-lint: 0 violations. Residual grep for the hostname, its two IPs, and the SSID across omp-docs/ and agent/managed-skills/: no hits.
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 the workstation.
|
|
|
|
```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
|