Stability AI gives developers access to their text generator in a next-generation image

The next generation of Stable Diffusion's text-to-image AI model is still in the preview stage, but Stability AI is making it available to some developers through an API and a new content creation platform. According to Stability AI, developers can now access Stable Diffusion 3 through its developer platform.

Stability AI says it is working with the Fireworks AI API platform for companies that want to use both models. In addition, the company plans to host weighting models on its own servers through its Stability AI membership "in the near future."

The company released Stable Diffusion 3 in February to a small number of developers in preview mode. Stability AI claims that Stable Diffusion 3 is "as good as or better than" other text-to-image generators, such as OpenAI's DALL-E 3 and Midjourney v6, in "typography and operational compliance." The model uses an architecture called Multimodal Diffusion Transformer, which should improve text comprehension and spelling.

Stability AI also announced a new content creation platform called Stable Assistant Beta, where Stable Diffusion 3 and other models will be available. According to the company, Stable Assistant Beta is a "friendly chatbot" where paid subscribers can access the latest models to create images, write content, or help match photos to text through conversation. For now, Stable Assistant Beta is not open to the public, but the company has invited a small number of users to try the release version in early access.

Despite being available through the API and the Stable Assistant beta, Stability AI says both Stable Diffusion 3 models remain in the preview stage and are not yet available to the general public. The company says it has expanded access to the models so it can work with the community to improve them, but it has "taken and continues to take reasonable steps to prevent misuse of Stable Diffusion 3 by bad actors."