Learn how to install ComfyStream using Docker or as a custom node for ComfyUI.
Install ComfyUI (if needed)
Install ComfyUI Manager (if needed)
Install ComfyStream via Manager
Restart ComfyUI
Manual Installation (Cloning Repository)
Windows
Install WSL 2
wsl --install
- Update WSL if
needed: wsl.exe --update
Launch Ubuntu in Terminal
Install NVIDIA CUDA Toolkit
Install Docker Desktop
Enable WSL 2 Engine in Docker
Verify Docker Access
docker ps
should return a result.Continue with setup
Create model and output directories
Pull the ComfyStream container
Run the container
--download-models
downloads some default models--build-engines
optimizes the runtime for your GPU--server
starts ComfyUI server (accessible on port 8188)--api
enables the API server--ui
starts the ComfyStream UI (accessible on port 3000)--use-volume
should be used with a mount point at /app/storage. It is used during startup to save/load models and compiled engines to a host volume mount for persistence--download-models
and --build-engines
flags are only needed the first time (or when adding new models).Access ComfyUI
Access ComfyStream UI
http://localhost:8889
and selecting a workflow.Launch the RunPod template
--use-volume
flag to save all models and engines to the mount path /app/storage
. A network volume is required.Create a network volume
Choose your GPU and deploy
Monitor deployment
Access ComfyUI
Open ComfyUI
Access ComfyStream UI
https://
followed by the IP:port for port 3000.You can start a live stream directly from the ComfyStream UI by keeping the stream URL as http://localhost:8889
and selecting a workflow.Create a cloud VM
Open required ports
Install Ansible
Clone the ComfyStream playbook
Add your VM IP to the inventory
inventory.yml
and add your VM’s public IP address.Set a custom password (optional)
comfyui_password
value in plays/setup_comfystream.yaml
.Run the playbook
--ask-become-pass
to enter your sudo password.Monitor download progress (optional)
Open ComfyUI
https://<VM_IP>:<PUBLIC_COMFYUI_PORT>
in your browser.0.0.0.0
.Docker Hub Rate Limits (toomanyrequests error)
toomanyrequests
error while pulling the Docker image, either
wait a few minutes or provide your Docker credentials when running the playbook: