Get the latest tech news
Stable Diffusion 3.5 follows your prompts more closely and generates more diverse people
The open-source AI image generator Stable Diffusion has been updated to version 3.5. It addresses previous issues, improves performance with prompts and offers a greater skin tone and feature diversity.
Finally, Stable Diffusion 3.5 Medium (2.5 billion parameters) is designed to run on consumer hardware, balancing quality with simplicity. The company admitted that the release “didn’t fully meet our standards or our communities’ expectations,” as it produced some laughably grotesque body horror in response to prompts that asked for no such thing. The company describes the new models’ human outputs as “representative of the world, not just one type of person, with different skin tones and features, without the need for extensive prompting.”
Or read this on Endgadget
