Stable Diffusion 3
Stable Diffusion 3, our most advanced image model yet, features the latest in text-to-image technology with greatly improved performance in multi-subject prompts, image quality, and spelling abilities.
The model is available via API today and we are continuously working to improve the model in advance of its open release. To learn more about deployment options please contact us.
Stable Diffusion XL
Get involved with the fastest growing open software project. Download and join other developers in creating incredible applications with Stable Diffusion XL as a foundation model.
SDXL Turbo
Discover the groundbreaking SDXL Turbo, the latest advancement from our research team. Built on the robust foundation of Stable Diffusion XL, this ultra-fast model transforms the way you interact with technology.
Read the Research Paper
Open, unbiased, and ready for the world
The next step in our mission to democratize AI and building a global foundation to activate humanity’s potential is to make our models as unbiased as possible. The introduction of our Japanese models is a clear step in that direction.
-
Japanese Stable Diffusion XL
A text-to-image model that emphasizes Japanese input to better understand Japanese culture. It comprehends Japanese expressions better than traditional English models, allowing for high-quality image generation that feels native.
Download Code
Learn More -
Japanese Stable VLM
Equipped with image captioning capabilities, this advanced Japanese image-language model can generate detailed Japanese descriptions for any image.
-
Japanese Stable Clip
A feature extraction model for zero-shot image classification and image search. Capable of classifying images without prior class information learning, it can also search for images based on any text.
Download Code
Learn More
Build with a Stability AI Membership
The Stability AI Membership offers flexibility for your generative AI needs by combining our range of state-of-the-art open models with self-hosting benefits.