Stability AI announces SDXL 1.0

Emre Çitak
Jul 27, 2023

Stability AI has released the latest version of its text-to-image algorithm, SDXL 1.0, which is more advanced than its predecessor, 0.9. The new version generates high-resolution graphics while using less processing power and requiring fewer text inputs. With Stable Diffusion XL 1.0, anyone can now create almost any image easily and effectively.

Just like ChatGPT, artificial intelligence tools have evolved to produce various types of media, including music, films, and pictures. SD and similar tools are already widely used, and the upgrades will improve their usage significantly.

According to the company's announcement, SDXL 1.0 is the best open model for photorealism and can generate high-quality images in any art style. It allows for absolute freedom of style, and users can prompt distinct images without any particular 'feel' imparted by the model. The new version is particularly well-tuned for vibrant and accurate colors, better contrast, lighting, and shadows, all in a native 1024×1024 resolution.

SDXL 1.0
SDXL 1.0 is the most powerful model of the popular generative image tool - Image courtesy of Stability AI

How to use SDXL 1.0

SDXL 1.0 is a large language model (LLM) from Stability AI that can be used to generate images, inpaint images, and create text-to-image translations. It is one of the largest LLMs available, with over 3.5 billion parameters.

To use SDXL 1.0, you can either use the Stability AI API or the Stable Diffusion WebUI. The API is a more powerful tool, but it requires some technical knowledge to use.

The WebUI is a more user-friendly interface, but it is not as powerful as the API.

Here are the steps on how to use SDXL 1.0 with the Clipdrop by Stability AI:

  1. Go to the Clipdrop Stability AI website
  2. Enter your prompt
  3. Click on generate

Once you have done this, the Stable Diffusion XL model will generate a custom image for you using SDXL 1.0. Clipdrop allows you to play with photos on a small scale, but if you want to control every aspect of your generation, you need to use the Satble Diffusions WebUI.

SDXL 1.0
You can access SDXL 1.0 using Clipdrop or via the Stable Diffusion WebUI - Image courtesy of Stability AI

Here are the steps on how to use SDXL 1.0 with the Stable Diffusion WebUI:

  1. Go to the Stable Diffusion WebUI GitHub page and follow their instructions to install it
  2. Download SDXL 1.0 via Hugging Face
  3. Add the model into Stable Diffusion WebUI and select it from the top-left corner
  4. Enter your text prompt in the "Text" field
  5. Enter the width and height of the image you want to generate in the "Width" and "Height" fields
  6. Click on the "Generate" button

The WebUI will generate an image based on your text prompt. The image will be displayed in the browser. You can save the image by clicking on the "Save" button.

SDXL has more features and possibilities than Midjourney due to its open-source nature. However, using it to its full potential can be challenging.

When it comes to quality, SDXL is one of the few commercially available image models that match the level of quality provided by Midjourney.


Tutorials & Tips

Previous Post: «
Next Post: «


  1. Anonymous Artist said on July 27, 2023 at 4:16 pm

    Does SDXL use copyrighted works in its training data?

Leave a Reply

Check the box to consent to your data being stored in line with the guidelines set out in our privacy policy

We love comments and welcome thoughtful and civilized discussion. Rudeness and personal attacks will not be tolerated. Please stay on-topic.
Please note that your comment may not appear immediately after you post it.