Stability AI today announced the availability of Stable Diffusion 3 and Stable Diffusion 3 Turbo as APIs for third-party developers, allowing them to add powerful image generation capabilities to their apps and services.
“We are pleased to announce the availability of Stable Diffusion 3 and Stable Diffusion 3 Turbo on the Stability AI Developer Platform API,” the announcement post explains. “This model is equal to or outperforms state-of-the-art text-to-image generation systems such as DALL-E 3 and Midjourney v6 in typography and prompt adherence, based on human preference evaluations … We aim to make the model weights available for self-hosting with a Stability AI Membership soon.”
Sign up for our new free newsletter to get three time-saving tips each Friday — and get free copies of Paul Thurrott's Windows 11 and Windows 10 Field Guides (normally $9.99) as a special welcome gift!
"*" indicates required fields
According to the firm, these models utilize a new Multimodal Diffusion Transformer (MMDiT) architecture that improves text understanding and spelling capabilities via separate sets of weights for image and language representations. And it has partnered with Fireworks AI, which it describes as “the fastest and most reliable API platform in the market,” to deliver these models as “an enterprise-grade API solution” that delivers 99.9% service availability.
Like other generative AI providers, Stability AI has also worked to ensure that the Stable Diffusion 3 APIs are safe and responsible. “Safety starts when we begin training our model and continues throughout the testing, evaluation, and deployment,” it notes. “By continually collaborating with researchers, experts, and our community, we expect to innovate further with integrity as we continue to improve the model.”
You can learn more on the Stability AI Platform Developer website.