serverAppConfigs/serverAppConfigs-docs/Dankclaw/ComfyUI.md

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 — Port: 8188 published on the host; no vhost and no guard chain — ComfyUI is LAN-only by construction (the Caddyfile routes no name to it) — Backend: ROCm GPU (gfx1151) — Docs: https://github.com/Comfy-Org/ComfyUI

Facts

Item	Value
Image	comfyui-rocm:gfx1151 — built from dankclaw/Containerfile.comfyui
Base image	docker.io/rocm/vllm:rocm7.12.0_gfx1151_ubuntu24.04_py3.12_pytorch_2.9.1_vllm_0.16.0
Port	8188 (host) → 8188 (container)
Backend	ROCm GPU (gfx1151 / Radeon 8060S). No --cpu flag.
Data	/home/dank/comfyui-data/{models,input,output,custom_nodes} → /opt/ComfyUI/...
Run	./scripts/deploy.sh dankclaw --service comfyui (Quadlet unit comfyui.service)
Boot-persistent	Quadlet unit dankclaw/comfyui/quadlet/comfyui.container → ~/.config/containers/systemd/

Why the GPU works here

Dankclaw is an AMD Strix Halo APU (gfx1151). Standard PyTorch ROCm wheels do not ship gfx1151 kernels. So torch.cuda.is_available() returns False and ComfyUI falls back to CPU. AMD publishes a gfx1151-tagged build, and the image above is based on it. On this APU it reports torch.cuda.is_available() = True, device Radeon 8060S, capability (11, 5). See ComfyUI ROCm and Vulkan for the full verification.

How the image is built

dankclaw/Containerfile.comfyui starts from the AMD gfx1151 base image and bakes the ComfyUI code in. It installs ComfyUI's dependencies but skips the torch family (torch, torchvision, torchaudio). The base image already ships the matching ROCm builds. Installing an unpinned torch from requirements.txt clobbers the gfx1151 kernels with a default build, so the Containerfile filters those lines out.

GPU device access (rootless), and why the unit exists

The unit passes /dev/kfd and /dev/dri (AddDevice=) and uses GroupAdd=keep-groups. A literal render entry cannot work: rootless Podman cannot map the group name into the user namespace. The companion udev rule dankclaw/udev/99-comfyui-gpu-access.rules keeps those nodes MODE 0666, which is what lets a user-unit spawn — carrying no supplementary groups — open them anyway. Verified inside the running container: torch.cuda.is_available() is True and the device is Radeon 8060S Graphics.

Incident, 2026-09-16 — why this is a Quadlet now. ComfyUI ran from dankclaw/compose.yaml through a hand-written ~/.config/systemd/user/ comfyui.service that called podman compose up -d. Its container was created before the GPU declarations were added to the compose service, and restart: unless-stopped then kept restarting that stale container: no /dev/kfd, no /dev/dri, no keep-groups, dead on RuntimeError: No HIP GPUs are available — 9,146 restarts and about seven hours down. The service was fine; the container was old. A --force-recreate would have fixed it that day, but the class of bug needed the unit: one owner per container name, repo-tracked, and recreated from the source of truth on every deploy. The compose service is deleted; deploy_comfyui retires any compose-era unit into ~/.AGENTTRASH/ and removes a stale container before installing the unit.

Volumes

Container path	Host path
/opt/ComfyUI/models	/home/dank/comfyui-data/models
/opt/ComfyUI/input	/home/dank/comfyui-data/input
/opt/ComfyUI/output	/home/dank/comfyui-data/output
/opt/ComfyUI/custom_nodes	/home/dank/comfyui-data/custom_nodes

The ComfyUI code is baked into the image (not mounted). Rebuild the image to update the code.

Custom nodes

Custom nodes go in /home/dank/comfyui-data/custom_nodes (mounted at /opt/ComfyUI/custom_nodes). ComfyUI loads every subdirectory there on start. Because this path is a bind mount, it shadows anything baked into the image — so custom nodes are installed host-side, not in the Containerfile.

ComfyUI-Manager is installed here. Install it with a one-time clone, then restart the container:

git clone https://github.com/ltdrdata/ComfyUI-Manager \
  /home/dank/comfyui-data/custom_nodes/ComfyUI-Manager
systemctl --user restart comfyui

ComfyUI-Manager self-installs its own pip dependencies on start (GitPython, PyGithub, matrix-nio, transformers, and more). To confirm it loaded, query GET /manager/version (returns a version like V3.41). Its pip installs live in the container's writable layer, so they survive a restart and a reboot but not an image rebuild; after a rebuild, Manager re-installs them on the next start.

Boot persistence

The Quadlet unit carries [Install] WantedBy=default.target with Restart=always, so the generator wires it into default.target and it comes back on its own (user linger is on). Inspect it with systemctl --user is-enabled comfyui.service → generated; an explicit systemctl --user enable fails on generated units.

Healthcheck

The web UI responds on /. ComfyUI also exposes /system_stats. On this APU, /system_stats reports device=cuda:0 Radeon 8060S Graphics (type cuda, the ROCm device).

Gotchas

• The GPU path needs the device passthrough. Do not remove AddDevice=/dev/kfd or AddDevice=/dev/dri from the unit, and keep GroupAdd=keep-groups.
• Do not add the render group by name. Rootless podman cannot map it; the udev rule plus keep-groups is the mechanism that works.
• A stale container outlives a compose edit. If the GPU declarations change, recreate the container (deploy.sh dankclaw --service comfyui removes the old one) — restart: unless-stopped will happily keep an old config alive forever.
• Do not let pip reinstall the torch family. The Containerfile filters it out on purpose.
• The base image is about 32 GB. A code update means a rebuild, because the code is baked in.
• The model collection starts empty. Add models to /home/dank/comfyui-data/models before generating.

See Also

• Dankclaw Stack
• ComfyUI ROCm and Vulkan — the live-verified GPU path research
• Lemonade and sd.cpp — the ggml-family alternative
• Knowledge base: ComfyUI (tools)