Stable Diffusion: Fooocus

System: Ubuntu 24.04
Edition: 010326

Stable Diffusion: Fooocus

Want to create high-quality images from text descriptions without dealing with complex interfaces, endless parameters, or technical details? Launch Fooocus on a ready-to-use cloud server with a GPU and start creating in just a few minutes.

This Ubuntu-based image features a fully configured Fooocus 2.5.5 environment — a minimalist yet powerful tool for image generation based on Stable Diffusion XL. Everything is ready to go: NVIDIA drivers, web access via nginx, and pre-loaded models. Simply rent a GPU server, open your browser, and start prompting.

Description

What's Included?

  • Fooocus 2.5.5 — Focus on simplicity and quality;

  • Stable Diffusion XL — A modern model with high-level detailing;

  • nvidia-driver 590.48.01 — Optimized for RTX 3090 / 4090 / 5090;

  • nginx — Provides stable browser-based access to the interface.

How It Works

Stable Diffusion is a generative neural network that creates images from text using the latent diffusion method: it step-by-step forms an image from random noise, guided by the meaning of your prompt. Trained on billions of captioned images, the model accurately links words to visual elements — colors, shapes, and composition.

Fooocus simplifies this process to the maximum: you describe the desired result, and the system automatically selects the style, parameters, and model. No sliders, no technical jargon — just pure creativity.


System Component Versions

Kernel:

Linux 6.17.0-14-generic #14~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Jan 15 15:52:10 UTC 2 x86_64 x86_64 x86_64 GNU/Linux

Operating System:

  • Distributor ID: Ubuntu

  • Description: Ubuntu 24.04.4 LTS

  • Release: 24.04

  • Codename: noble

Category:
Base Linux / Neural Networks
Size:
93.44 GB
Image added:
01.03.2026
Image updated:
01.03.2026
Uses:
1

Getting started

Recommended Configurations

Model / Use Case Recommended GPU VRAM Amount
Base Generation (512×512)

NVIDIA RTX 3090

8 ГБ

SDXL, High Quality

NVIDIA RTX 4090

12 ГБ

Fast Generation + Styles

NVIDIA RTX 4090 / 5090

16 ГБ

Base Generation (512×512)

NVIDIA RTX 3090

8 ГБ

SDXL, High Quality

NVIDIA RTX 4090

12 ГБ

For a smooth experience with SDXL in Fooocus, it's best to choose an RTX 4090 or 5090 — this will ensure instant response times and support for high resolutions.


By renting a GPU server for AI at immers.cloud, you get:

  • A ready-to-use workstation in just 2 minutes;

  • Per-second billing — pay only for the time the server is actually in use;

  • Access to powerful GPUs: RTX 4090, 5090, A10, and others.

Connection

To connect, wait until the "StableDiffusion" link appears under your server's IP address. Clicking this link will redirect you to the Fooocus interface.

Please note that access is provided via a link containing a token, which is required for proper authentication. If you wish to share access with someone else, you must copy the entire URL, including the ?token= parameter.

How to Write a Prompt

To achieve the best results, clearly describe what you want to see. A typical prompt structure looks like this: [subject], [action or pose], [background], [style], [quality], [details]

Example:

a futuristic warrior in a glowing armor, standing on a cliff, cinematic lighting, volumetric fog, ultra detailed, artstation

You can use commas or brackets to set priorities. Negative prompts are also supported, allowing you to exclude unwanted elements from your image.