Frank
e3eb5334cb
- Dankserver stack: RomM, Copyparty, Calibre-Web, node-exporter - Dankclaw stack: Gluetun VPN (SearXNG tunnel), SearXNG+Valkey, ComfyUI (CPU backend), OpenWebUI, Hermes, Gitea+Postgres (migrated), Caddy reverse proxy, Grafana+Prometheus+Loki+Alloy observability - Caddyfiles with .local hostname convention and basicauth homepage - bind-mount storage policy, no named volumes - deploy.sh mirroring vllmScripts git workflow (push -> pull -> restart -> health) - docs/ Obsidian vault: per-service docs from frank-default-small research subagents (promtail EOL -> Alloy; gitea SECRET_KEY preservation; ComfyUI --cpu) - bats test suite at 6 seams — 22 tests green
54 lines
2.2 KiB
Markdown
54 lines
2.2 KiB
Markdown
# ComfyUI
|
|
|
|
ComfyUI is a node-based AI image generation engine. Workflows are built from nodes that load models, sample latents, and post-process images; everything is scriptable through a web UI and an API.
|
|
|
|
**Host:** Dankclaw — **Hostname:** `comfyui.dankclaw.local` — **Port:** 8188 — **Docs:** https://github.com/Comfy-Org/ComfyUI
|
|
|
|
## Facts (from research, primary source)
|
|
|
|
| Item | Value |
|
|
|------|-------|
|
|
| Image | `ghcr.io/comfyanonymous/comfyui:latest` (community CPU build) |
|
|
| Port | 8188 (host) → 8188 (container) |
|
|
| Models volume | bind mount to the model collection |
|
|
| CPU flag | `--cpu` — confirmed in `cli_args.py`: "To use the CPU for everything (slow)" |
|
|
| Known issue | ROCm wheels do not ship kernels for gfx1151 (Strix Halo) — CPU backend required |
|
|
|
|
## Why CPU on Dankclaw
|
|
|
|
Dankclaw is an AMD Strix Halo APU (gfx1151). Precompiled ROCm PyTorch wheels do not support this iGPU. This matches the existing knowledge base entry for ComfyUI on Dankclaw: the running instance uses `--cpu`. The Docker image for CPU execution is the `comfyui` CPU build; the GPU images (`comfyui-cuda`) must not be used.
|
|
|
|
## Command Line (from `cli_args.py`)
|
|
|
|
| Flag | Meaning |
|
|
|------|---------|
|
|
| `--cpu` | use CPU for everything |
|
|
| `--cpu-vae` | run the VAE on CPU only |
|
|
| `--lowvram` | text encoders on CPU (dynamic VRAM default handles this) |
|
|
| `--listen` | bind address (0.0.0.0 for LAN) |
|
|
| `--port` | listen port (8188) |
|
|
|
|
## Volumes
|
|
|
|
| Container path | Host path (convention) |
|
|
|----------------|------------------------|
|
|
| `/workspace` | `/opt/comfyui` (models, input, output, custom_nodes) |
|
|
|
|
## Start Fresh
|
|
|
|
The model collection starts from scratch. The first boot creates the directory structure; models are added per the knowledge base procedure.
|
|
|
|
## Healthcheck
|
|
|
|
The web UI responds on the root path `/`. ComfyUI also exposes `/system_stats`.
|
|
|
|
## Gotchas
|
|
|
|
- Expect minutes per image on CPU; that is the documented behavior for this APU.
|
|
- ComfyUI-Manager installs custom nodes into `custom_nodes/` — persist that directory.
|
|
- Do not pull the CUDA image; it fails to find an NVIDIA driver.
|
|
|
|
## See Also
|
|
|
|
- [[Dankclaw Stack]]
|
|
- Knowledge base: [[ComfyUI]] (tools), [[ComfyUI Troubleshooting]] |