ComfyUI Image Generator with Stable Diffusion & NVIDIA Drivers

LAUNCH NOW WRITE A REVIEW

Please feel free to contact us

About

ComfyUI is a highly flexible, powerful, and user-friendly node-based interface for Stable Diffusion that enables advanced AI image generation workflows with ease. Built for performance and transparency, ComfyUI allows users to visually construct custom pipelines for text-to-image generation, inpainting, image-to-image transformations, upscaling, and more — all without writing a single line of code.

Unlike traditional interfaces, ComfyUI uses a modular, drag-and-drop workflow where each node represents a specific step in the generation process, such as model loading, prompt input, sampling, or post-processing. This makes it easy to understand exactly how images are created and to fine-tune or modify each stage of the process independently. It’s especially suited for users who want full control over every parameter while maintaining a clear visual understanding of their AI pipeline.

ComfyUI supports a wide range of Stable Diffusion models and extensions and is compatible with GPU-accelerated environments, enabling fast and efficient generation. It also includes support for features such as LoRA models, ControlNet, image upscaling, prompt weighting, and batch processing — making it ideal for both casual users and professional AI artists or developers.

Features:

ComfyUI pre-installed and optimized

Stable Diffusion engine included

Compatible with NVIDIA GPU EC2 instances

Fast and easy deployment on AWS

No additional setup required

Type virtual machines in the search.
Under Services, select Virtual machines.
In the Virtual machines page, select Add. The Create a virtual machine page opens.
In the Basics tab, under Project details, make sure the correct subscription is selected and then choose to Create new resource group. Type myResourceGroup for the name.*.
Under Instance details, type myVM for the Virtual machine name, choose East US for your Region, and choose Ubuntu 18.04 LTS for your Image. Leave the other defaults.
Under Administrator account, select SSH public key, type your user name, then paste in your public key. Remove any leading or trailing white space in your public key.
Under Inbound port rules > Public inbound ports, choose Allow selected ports and then select SSH (22) and HTTP (80) from the drop-down.
Leave the remaining defaults and then select the Review + create button at the bottom of the page.
On the Create a virtual machine page, you can see the details about the VM you are about to create. When you are ready, select Create.

It will take a few minutes for your VM to be deployed. When the deployment is finished, move on to the next section.

Connect to virtual machine

Create an SSH connection with the VM.

Select the Connect button on the overview page for your VM.
In the Connect to virtual machine page, keep the default options to connect by IP address over port 22. In Login using VM local account a connection command is shown. Select the button to copy the command. The following example shows what the SSH connection command looks like:

ssh azureuser@<ip>

Using the same bash shell you used to create your SSH key pair (you can reopen the Cloud Shell by selecting >_ again or going to https://shell.azure.com/bash), paste the SSH connection command into the shell to create an SSH session.

Usage/Deployment Instructions

After successfully connecting via SSH, you’re ready to set up ComfyUI Image Generator with Stable Diffusion & NVIDIA Drivers. Here’s how to get everything running:

Goto below path:

cd /home/niles/ComfyUI

source venv/bin/activate # Activate virtual environment

(venv) root@comfy:/home/niles/ComfyUI# python3 main.py –listen –port 8188 # Allows external connections # Add –cpu if GPU not available

# Press Ctrl+A then D to detach

Run in the Background (Optional)
Use nohup to keep it running after closing the terminal:
nohup python main.py &