Question 1

What is InvokeAI?

Accepted Answer

InvokeAI is a self-hosted studio for generating images with Stable Diffusion, running on your own server. It wraps local diffusion in a polished web interface with text-to-image and image-to-image generation, an infinite canvas for inpainting and outpainting, fine control over generation settings, a…

Question 2

Which port does it use and is there a login?

Accepted Answer

InvokeAI runs on host port 9190, mapped from the container's 9090. There's no built-in authentication, so anyone who can reach the port has full use of the studio and your hardware. Keep it on your LAN or behind an authenticating reverse proxy, and never expose port 9190 directly to the internet.

Question 3

Do I need a GPU?

Accepted Answer

In practice, yes. Image diffusion is heavily GPU-bound — an image takes seconds on an NVIDIA GPU but many minutes on CPU, which makes CPU generation impractical for real work. InvokeAI can technically run on CPU, but you'll want an NVIDIA GPU and the nvidia-container-toolkit for usable speed.

Question 4

Why is generation so slow?

Accepted Answer

Almost certainly because it's running on CPU. This deployment doesn't set up GPU passthrough automatically, so unless you've configured the container to access an NVIDIA GPU, diffusion falls back to the CPU, where it's extremely slow.

Question 5

How does it compare to ComfyUI?

Accepted Answer

Both run Stable Diffusion locally and need a GPU, but they differ in philosophy. InvokeAI offers a polished, unified studio that's approachable and creative-focused.

🤖 Setup InvokeAI — Self-Hosted Stable Diffusion Studio

📦 Resources & Setup Scripts

Quick Install:

Tutorial Steps

1 Download the Script

2 Make it Executable

3 Run the Installer

4 Open the Studio and Install a Model

Ports Used

Overview

Why Use It

When You Need It

Who Should Use It

Real Use Cases

Main Features

How to Use After Installation

Security Best Practices

Ports and Firewall Notes

Backup and Maintenance

Common Mistakes

Troubleshooting

Alternatives

When Not to Use It

PrismaTechWork Professional Help

Frequently Asked Questions