Stable Diffusion 3 API Now Available

Key Takeaways

  • Stable Diffusion 3 and Stable Diffusion 3 Turbo are now available on the Stability AI Developer Platform API

  • We have partnered with Fireworks AI, the fastest and most reliable API platform in the market, to deliver Stable Diffusion 3 and Stable Diffusion 3 Turbo.

  • In keeping with our commitment to open generative AI, we aim to make the model weights available for self-hosting with a Stability AI Membership in the near future.

We are pleased to announce the availability of Stable Diffusion 3 and Stable Diffusion 3 Turbo on the Stability AI Developer Platform API

As revealed in the Stable Diffusion 3 research paper, 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. 

The new Multimodal Diffusion Transformer (MMDiT) architecture uses separate sets of weights for image and language representations, which improves text understanding and spelling capabilities compared to previous versions of Stable Diffusion.

While the model is available via API today, we are continuously working to improve the model in advance of its open release. In keeping with our commitment to open generative AI, we aim to make the model weights available for self-hosting with a Stability AI Membership soon.

To learn more about deployment options please contact us here. To get started with the Stable Diffusion 3 API, visit the documentation page

We’re also inviting a limited number of users to participate in the early release of our Stable Assistant Beta, featuring Stable Diffusion 3. In its limited release, Stable Assistant enables content creation with Stability AI’s cutting-edge image and language models. 

Performance

We have partnered with Fireworks AI, the fastest and most reliable API platform in the market, to deliver Stable Diffusion 3 and Stable Diffusion 3 Turbo.

With Fireworks AI, we will also deliver an enterprise-grade API solution that ensures 99.9% service availability—essential for enterprises relying on our developer platform for their most important generative AI workloads. Our customers can confidently utilize our services for their mission-critical operations.

Safety

We believe in safe, responsible AI practices. This means we have taken and continue to take reasonable steps to prevent the misuse of Stable Diffusion 3 by bad actors. Safety starts when we begin training our model and continues throughout the testing, evaluation, and deployment. By continually collaborating with researchers, experts, and our community, we expect to innovate further with integrity as we continue to improve the model. 

With Stable Diffusion 3, we strive to offer adaptable solutions that enable individuals, developers, and enterprises to unleash their creativity, aligning with our mission to activate humanity’s potential.

Get started with Stable Diffusion 3 on the Stability AI Developer Platform API here. To learn more about enterprise deployment options, including self-hosting, please contact us here.

To stay updated on our progress follow us on Twitter, Instagram, LinkedIn, and join our Discord Community.

Previous
Previous

Stability AI Joins Thorn and All Tech Is Human to Enact Child Safety Commitments for Generative AI

Next
Next

MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data