Stable Diffusion 3 and Stable Diffusion 3 Turbo are now available on the Stability AI Developer Platform API, surpassing DALL-E 3 and Midjourney v6 in text-to-image generation. The new Multimodal Diffusion Transformer architecture improves text understanding and spelling capabilities. The model is continuously being enhanced, with plans to release model weights for self-hosting soon. A limited release of Stable Assistant Beta offers users early access to cutting-edge image and language models. Partnered with Fireworks AI for reliable service delivery, Stability AI assures 99.9% service availability for mission-critical operations. Emphasizing safe AI practices, the company is committed to preventing misuse and collaborating with experts for continuous improvement.
https://stability.ai/news/stable-diffusion-3-api