Stable Diffusion, FLUX.1: ComfyUI

System: Ubuntu 24.04
Edition: 140226

A ready-made environment for generating images directly in the browser

Description

Do you want to start creating images with neural networks right away — without installing drivers, dependencies, or setting up a Python environment? Launch a virtual machine with a GPU on immers.cloud and get a ready-to-use environment for generative AI directly in your browser!

This image, based on Ubuntu 24.04.3, includes everything you need to work with Stable Diffusion, FLUX.1, SDXL, WAN, LTX-2, and other modern models. Everything is pre-configured: NVIDIA drivers, ComfyUI, an extension manager, and a reverse proxy via nginx. 

Who is this image for?

  • Artists and designers who want to use Stable Diffusion and FLUX.1 without setting up the environment;
  • Developers creating custom generation pipelines through a visual editor;
  • Teams needing a server rental for a quick start;
  • Those looking for neural network servers with instant access and full compatibility.

What's inside?

  • ComfyUI — a powerful visual interface for building complex generation graphs;
  • Pre-loaded models: FLUX.1, Stable Diffusion 1.5/SDXL, WAN, LTX-2;
  • ComfyUI Manager — for easy management of extensions and nodes;
  • NVIDIA drivers 590.48.01 — optimized for RTX 4090, 5090, and other powerful GPUs;
  • nginx — provides stable browser access to the interface.

Why is it so fast?
Stable Diffusion is an open-source generative neural network developed by Stability AI in 2022. It creates images from text descriptions using a latent diffusion method: first, the model adds noise to a random image, and then gradually restores it, guided by the semantics of the prompt. Thanks to its open license, it can be freely run on your own resources — for example, on a cloud platform with a GPU.

Tip: For maximum generation speed, choose NVIDIA 4090 or 5090 — these graphics cards deliver up to 60+ images per minute even at high resolutions. For working with FLUX, SDXL, and video models, we recommend choosing Tesla-series graphics cards: A100, H100, and H200 due to the device memory requirements of very large models.

System Components

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:
51.05 GB
Image added:
14.02.2026
Image updated:
14.02.2026
Uses:
33
Avg boot time:
00:28 — 00:41

Getting started

Connection

To connect, wait until the "StableDiffusion" link appears under your server's IP Address. Clicking the link will redirect you to the ComfyUI interface. Please note that access is provided via a link containing a token, which is necessary for proper authentication. If you wish to share access, you need to copy the full link, which includes the Token.

Access to the ComfyUI API

Access to the API is provided on port :8000 by passing the X-API-Key header, for example:

curl http://ip.address.of.your.server:8000/api/queue -H "X-API-Key: Your-token"

You can see the token in the connection link on your server's page: http://ip.address.of.your.server/?token=your-token.
The token is also available in the /root/.immerstoken file.