SDXL TurboBeta

Real-Time Text-to-Image Generation

All tools

Frequently Asked Questions

What is Stable Diffusion XL Turbo?

SDXL Turbo is a text-to-image model developed by the Stability AI research team based on Stable Diffusion XL model.

SDXL Turbo uses Adversarial Diffusion Distillation (ADD) technology to achieve real-time text-to-image generation by synthesizing images in a single step.

SDXL Turbo model weights & code are available on Hugging Face. You can read more here.

What is Stable Diffusion XL?

Stable Diffusion XL 1.0 (SDXL 1.0) is the most advanced development in the Stable Diffusion text-to-image suite of models launched by Stability AI.

SDXL 1.0 is released under the CreativeML OpenRAIL++-M License dated July 26, 2023. Details on this license can be found here.

The weights of SDXL 1.0 and the associated source code have been released on the Stability AI Github page.

How to generate images from text?

Stable Diffusion models can take an English text as an input, called the "text prompt", and generate images that match the text description. These kinds of algorithms are called "text-to-image".

First, describe what you want, and Clipdrop Stable Diffusion XL will generate four pictures for you. You can also add a style to the prompt, aspect ratio and model version.

Then you can retry until you find the perfect image or keep customizing your text prompts.

When you find an image that works, you can download it!

What does the “Not safe for work image detected” message mean?

To ensure this experience can be used by all audiences, we implemented a filter that blurs images if they are detected as potentially NSFW.

We are constantly working on our safety filters and are committed to improving them over time.