| System: | Ubuntu 22.04 |
| Edition: | 140525 |
A ready-made environment for generating images directly in the browser
You get a customized system based on Ubuntu 22.04.5 with the ComfyUI interface, a visual editor for creating complex image generation graphs. Everything works through the browser: you don't need to install or configure anything manually. Just start the server and start generating.
The image is suitable if you want:
What's inside the image:
What is Stable Diffusion and how does it work?
Stable Diffusion is an open source generative neural network. It creates images based on a text query. The algorithm is trained on billions of images and is able to "understand" words by comparing them with visual forms.
The work is based on the LA method
To connect, copy your server's IP address into the browser's address bar.
To quickly get started with FLUX, click on the "Workflows" tab in the ComfyUI interface and select Flux in the "immersions.cloud" section.
If you are using large models (SDXL or any other large models), you must select a configuration with a large amount of RAM. For FLUX, the recommended size is 64GB, and the minimum is 32GB. For SDXL, we recommend paying attention to configurations with 32 or 64GB of RAM. Otherwise, there may be problems in operation, such as periodic shutdowns of StableDiffusion. When working with small models such as StableDiffusion 1.5, StableDiffusion 2.1, this problem is absent.
To get a high-quality image, it is important to formulate a text query correctly. It should describe:
Query example: black cat among books, Fantasy art style, warm tones, high detail, soft light.