ComfyUI

Deploy ComfyUI, the node-based Stable Diffusion UI, as a template on a GPU instance. Aquanode provisions and starts it for you behind a private, password-protected URL.

ComfyUI is a node-based interface for Stable Diffusion image and video generation. Aquanode runs it as a template: pick it when you deploy a GPU instance and it starts automatically on boot, served behind a password-protected URL. You don't install or configure anything on the box yourself.

What you can do

Launch ComfyUI on a GPU instance with no manual setup
Access it from your browser over a private URL with auto-generated login credentials
Use any GPU from the marketplace that fits your models

Deploy ComfyUI

Pick a GPU

Go to the Marketplace and choose a GPU offer. ComfyUI runs on the VM you deploy, so pick a GPU with enough VRAM for the models you plan to run.

Select the ComfyUI template

In the deploy configuration panel, open the Template dropdown and choose ComfyUI. Set a deployment name and adjust resources if needed, then deploy.

The service starts on boot

You don't need to do anything on the instance. Aquanode provisions the box, installs ComfyUI, and starts it automatically once the VM is ready.

Open ComfyUI

When the deployment reaches Ready, open it from Deployments and go to the Overview tab. The ComfyUI section shows:

An Open button (and the URL, with a copy button)
A Username and Password to sign in

Click Open, enter the username and password, and ComfyUI loads in your browser.

Access details

ComfyUI is served on port 5188 behind HTTP basic authentication, so it is not open to the public, only to someone with the credentials shown on your deployment.
The username and password are generated automatically per deployment and displayed on the Overview tab.
The service status (running / starting) is shown alongside the credentials.

The instance bills until you close it

A ComfyUI deployment is a running GPU instance. It keeps billing until you close the deployment from the console. Close it when you're done.