| System: | Ubuntu 24.04 |
| Edition: | 140226 |
Create Stable Diffusion images with FLUX.1 in your browser with Automatic1111 Forge
This image contains Automatic1111 Forge — a more advanced version of Automatic1111 with new functionality.
The image supports the latest model versions, including Flux, which ensures high quality and fast generation times.
What's inside:
Ubuntu 24.04 image with pre-installed Automatic1111 Forge for flexible image creation customization, including pre-installed models. It includes:
Automatic1111 Forge
nvidia-driver
nginx
Stable-Diffusion Models
What is Stable Diffusion and how does it work?
Stable Diffusion is a neural network created for generating images from text descriptions. It uses a latent diffusion method to gradually "restore" an image from random noise, guided by the meaning of the text.
The technology is based on a large training dataset — billions of captioned images. The model analyzes these and learns to connect words with visual elements: shapes, colors, styles.
Automatic1111 runs on Stable Diffusion but makes the entire process simpler. The user only needs to describe what they want to see — the program itself determines the necessary parameters and model. This lowers the entry barrier and allows you to focus on creativity.
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
How to connect?
To connect, wait until the "StableDiffusion" link appears under your server's IP Address. Clicking the link will redirect you to the Forge interface.
Please note that access is provided via a link with a token, which is necessary for correct authentication. If you want to share access, you need to copy the full link, which includes the ?token= part.
Which configuration should I choose?
When using large models (SDXL or any other large-sized models), you must select a configuration with a large amount of RAM. We recommend considering configurations with 32, 64, or 128 GB of RAM. Otherwise, you may encounter operational issues, such as periodic disconnections of StableDiffusion. This problem does not occur when working with small models, such as StableDiffusion 1.5 or StableDiffusion 2.1.
How to compose a prompt?
To get a good result, clearly describe what you want to see. The structure of a prompt usually 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 also work, allowing you to exclude unwanted elements.