Stability AI's text-to-image model now available to more developers
What's the story
Stability AI is broadening the accessibility of its text-to-image AI model, Stable Diffusion 3, to a larger group of developers. The model, still in its preview phase, can now be accessed via an API and a new content creation platform, on the Stability AI Developer Platform. Initially launched in February for a select group of developers, Stable Diffusion 3 can match or even outperform similar generators like OpenAI's DALL-E 3 and Midjourney v6 in areas like "typography and prompt adherence."
Strategic collaboration
Partnership with Fireworks AI, plans for future
Stability AI is collaborating with API platform Fireworks AI to cater to businesses interested in leveraging both models. Furthermore, the company has plans to store its model weights on its proprietary servers through a Stability AI membership in the near future. The model uses an architecture, known as Multimodal Diffusion Transformer, which is designed to enhance text comprehension and spelling accuracy.
Twitter Post
Take a look at Stability AI's post
Today, we
are pleased to announce the availability of Stable Diffusion 3 and Stable Diffusion 3 Turbo on the Stability AI Developer Platform API.
We have partnered with @FireworksAI_HQ , the fastest and most reliable API platform in the market,to deliver these models. — Stability AI (@StabilityAI) April 17, 2024
In… pic.twitter.com/4q4wUf870Q
Platform launch
A new content creation platform
Stability AI has also unveiled a new content creation platform, Stable Assistant Beta, which will incorporate Stable Diffusion 3 among other models. According to the company's statement, Stable Assistant Beta functions as a user-friendly chatbot where paid subscribers can interactively access the latest models to generate images, compose content or pair photos with text. However, despite expanding access through the API and Stable Assistant Beta, Stability AI stresses that both versions of Stable Diffusion 3 are still in preview mode.