When you purchase through links on our site, we may earn an affiliate commission.Heres how it works.
StabilityAI is today releasing its new Stable Diffusion 3.5 family of AI image models.
It comes with improved realism, prompt adherence and text rendering compared to SD3.
AI image made with SD3.5 by Tom’s Guide
In short, this is a big step towards any user being able tocreate more realistic AI images.
What’s new with Stable Diffusion 3.5?
Stability AI says the models included are focused on customizability, efficient performance, and diverse outputs.
AI image made with SD3.5 by Tom’s Guide
It is a huge step up from SD3, especially the medium version.
There’s also a focus on new stylistic choices, including photography, painting, and more.
It takes in hashtag prompts to specify a style such as boho or fashion.
SD3.5 image from Tom’s Guide(Image credit: StabiltyAI/Future AI)
It can also use highlighting within the prompt to steer the model in a specific direction.
Anything beyond that will require an Enterprise Licence.
Dim candlelight and flickering shadows in an old library setting.
SD3.5 image from Tom’s Guide(Image credit: StabiltyAI/Future AI)
A glowing golden temple is barely visible in the distance, hidden among the trees.
Soft sunlight filtering through the scene.
SD3.5 image from Tom’s Guide(Image credit: StabiltyAI/Future AI)
SD3.5 image from Tom’s Guide(Image credit: StabiltyAI/Future AI)
SD3.5 image from Tom’s Guide(Image credit: StabiltyAI/FutureAI)
