How to generate images with Stable Diffusion on your server
Updated 7/20/2026
Stable Diffusion generates images from text, running on your server. No subscriptions and no generation limits.
You need a GPU
Image generation requires a GPU for reasonable speed, see the GPU plans and when you need a GPU.
1. The AUTOMATIC1111 interface
The most popular web interface for Stable Diffusion. You install it with the official script on a server with a GPU and NVIDIA drivers installed.
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
cd stable-diffusion-webui
./webui.sh --listen2. Access the interface
The interface runs on port 7860. You write a prompt, choose the settings and generate.
3. Securing it
Do not leave the interface public without protection. Use a reverse proxy with authentication and HTTPS.
Hourly billing
If you generate images only occasionally, with hourly billing you start the GPU server for the work session and stop it after, without paying around the clock for a GPU.
Put this guide into practice on your own VPS
EU cloud servers, billed hourly, ready in minutes, with one-click installs for dozens of apps.
See pricingRelated tutorials
How to use OpenHands as an AI software engineer
OpenHands takes a task and writes, runs and debugs the code on its own. Here is how to use it safely.
Updated 7/20/2026AI & self-hostingHow to extract web data without code, using Maxun
Build robots that collect data from websites by clicking, without writing a line of code.
Updated 7/20/2026AI & self-hostingHow to build a customer chatbot with Dify
Use Dify to create an assistant that answers from your company documents, without writing code.
Updated 7/20/2026