ComfyStream is available as a custom node through the ComfyUI Manager or as a Docker image. Follow the method that best suits your setup.

ComfyUI Manager (Recommended)

Install ComfyStream directly into an existing ComfyUI setup.

Docker (Self-contained)

Run ComfyStream and ComfyUI together in a prebuilt Docker container.

​
Install with ComfyUI Manager

If you already have ComfyUI installed, the easiest way to install ComfyStream is via the built-in ComfyUI Manager.

1

Install ComfyUI (if needed)

Download and install ComfyUI if you haven’t already.

Currently comfystream works only with the hiddenswitch fork of ComfyUI, the team is actively working add full support for official ComfyUI.

2

Install ComfyUI Manager (if needed)

Follow the ComfyUI Manager installation guide if you haven’t already.

3

Install ComfyStream via Manager

  1. Launch ComfyUI.
  2. Open the Manager tab.
  3. Search for ComfyStream and click Install.
4

Restart ComfyUI

Restart your ComfyUI server to load the new custom node.

​
Install with Docker

Run ComfyStream in a prebuilt Docker environment, either on your own GPU or a cloud server.

Local GPU

Run ComfyStream locally with your own GPU.

Remote GPU

Deploy ComfyStream on a remote GPU using RunPod or Ansible.

​
Local GPU

If you have a compatible GPU on Windows or Linux, you can run ComfyStream locally via Docker.

​
Prerequisites

First, install the required system software:

​
Run the Docker Container

1

Create model and output directories

These folders store your models and generated outputs. Docker mounts them into the container.

mkdir -p ~/models/ComfyUI--models ~/models/ComfyUI--output
2

Pull the ComfyStream container

docker pull livepeer/comfystream:stable

If using Windows, ensure Docker Desktop is running first.

3

Run the container

docker run -it --gpus all \
  -p 8188:8188 \
  -p 8889:8889 \
  -p 5678:5678 \
  -v ~/models/ComfyUI--models:/workspace/ComfyUI/models \
  -v ~/models/ComfyUI--output:/workspace/ComfyUI/output \
  livepeer/comfystream:stable --download-models --build-engines --server

The --download-models flag downloads some default models.
--build-engines optimizes the runtime for your GPU.
These are only needed the first time (or when adding new models).

4

Access ComfyUI

Open your browser and go to http://localhost:8188 to start using ComfyUI with ComfyStream.

​
Remote GPU

If you don’t have a local GPU, you can run ComfyStream on a cloud server. Choose between a managed deployment with RunPod or manual setup using Ansible.

​
Run with RunPod

RunPod provides a simple one-click deployment of ComfyStream in a managed container environment — perfect for testing or avoiding manual setup.

1

Launch the RunPod template

Use this template to get started: livepeer-comfystream

Initial deployment to a network volume may take 20-45 minutes. For faster startup without data persistence, use the no-volume version.

2

Create a network volume

When using the persistent template, create and attach a network volume.

3

Choose your GPU and deploy

Select a suitable GPU (e.g. RTX 4090), then click Deploy On-Demand.

4

Monitor deployment

Use the Logs button to watch the container spin up.

5

Access ComfyUI

Once running, click Connect from the pod dashboard.

6

Open ComfyUI

Click the HTTP Service → :8188 link. It will open in a new browser tab.

​
Deploy with Ansible

Use Ansible to deploy ComfyStream to your own cloud VM (like AWS, GCP, Azure, or TensorDock). Great if you want more control or a repeatable, fully automated setup.

1

Create a cloud VM

Provision a VM with at least:

  • GPU: 20GB VRAM
  • RAM: 16GB
  • CPU: 4 vCPUs
  • Disk: 100GB
2

Open required ports

Allow incoming traffic on:

  • 22 (SSH – internal port)
  • 8189 (ComfyStream HTTPS – internal port)

Ensure your cloud provider maps these to public ports. Internal port 8189 is proxied to 8188, which serves the ComfyUI interface.

3

Install Ansible

Install Ansible on your local machine (not the VM). See the official installation guide.

4

Clone the ComfyStream playbook

git clone https://github.com/livepeer/comfystream.git
cd comfystream/scripts/ansible

No need to install anything on the VM — Ansible sets it all up over SSH.

5

Add your VM IP to the inventory

Open inventory.yml and add your VM’s public IP address.

6

Set a custom password (optional)

Edit the comfyui_password value in plays/setup_comfystream.yaml.

This sets the password used to access ComfyUI in your browser.

7

Run the playbook

ansible-playbook -i inventory.yaml plays/setup_comfystream.yaml

If you’re not using a root user, add --ask-become-pass to enter your sudo password.

The playbook pulls a ~20GB Docker image on the VM. This may take a while on first run.

8

Monitor download progress (optional)

If needed, SSH into the VM and run:

docker pull livepeer/comfystream:latest

Helpful if you’re unsure whether the download is progressing during first-time setup.

9

Open ComfyUI

Visit https://<VM_IP>:<PUBLIC_COMFYUI_PORT> in your browser.

​
Accessing ComfyStream

  1. Click the ComfyStream menu button in ComfyUI:

  2. Open Server Settings to verify that ComfyStream is configured to bind to the correct interface and port.

    For remote environments like RunPod, set the Host to 0.0.0.0.

  3. Click Save to apply the settings.

  4. Open the ComfyStream menu again and click Start ComfyStream Server. Wait for the server status indicator to turn green.

    You can monitor ComfyStream server logs in the ComfyUI log terminal tab.

  5. Click Open ComfyStream UI to launch it in a new tab. Alternatively, double-click the node graph and search for ComfyStream UI Preview.

​
Troubleshooting