Open source image generator Sable Diffusion has been updated to version 3.5 and fixes some bugs.
Stable Diffusion has been updated to version 3.5. The new AI image generator model processes prompts more accurately than other generators and rivals many large models in output quality. In addition, that output now displays a greater diversity of styles and skin colors without the user having to explicitly ask for them.
Three models
The most powerful of the three is Stable Diffusion 3.5 Large, which delivers the highest quality and follows industry user prompts. The Large model is intended for professional use with a resolution of 1 MP.
Then there is the lightweight version of the Large model, called Large Turbo, which focuses more on efficiency than maximum quality. Finally, there is the Medium model designed to run on consumer hardware. Quality and simplicity are perfectly balanced. You can easily generate images with it at a resolution between 0.25 and 2 megapixels. The last model will not be released until October 29, the first two are already available now.
In April, Stable Diffusion proposed their first video model that can turn one video into new videos from eight different perspectives. Since June, that model has been available on Hugging Face.