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 — Hostname: comfyui.dankclaw.local — Port: 8188 — 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	podman compose -f dankclaw/compose.yaml up -d comfyui
Boot-persistent	user systemd unit comfyui.service (runs the compose up at boot)

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)

The container reaches the GPU through the /dev/kfd and /dev/dri device passthrough. The permission is checked host-side. The run user is already a member of the render group on the host, so the device is readable.

Only the video group is added to the container. The render group (gid 990) is not added. Rootless podman cannot map it into the container namespace (the subgid range is 100000+), so --group-add render fails to start the container.

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 user systemd unit ~/.config/systemd/user/comfyui.service runs podman compose -f /home/dank/serverAppConfigs/dankclaw/compose.yaml up -d comfyui at boot. It sets WantedBy=default.target, and user linger is on. The old CPU venv unit is preserved at comfyui.service.venv.bak as a fallback.

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 /dev/kfd or /dev/dri from the compose service.
• Do not add the render group to the container. Rootless podman cannot map it. Add only video.
• 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)