Stability AI announced the release of Stable Diffusion, a text-to-image AI model, to researchers with public access coming soon.
Developed in collaboration with Hugging Face, Runway, and other communities, the model aims to democratize image generation.
Stable Diffusion can generate high-quality 512x512 images in seconds on consumer GPUs with under 10 GB VRAM.
The model was trained on LAION-Aesthetics, part of the LAION 5B dataset, and has undergone testing with over 10,000 beta testers.
The launch signifies a commitment to open-source standards and collaboration in AI, with further model releases and research anticipated.

Stability AI is a startup focused on creating state-of-the-art artificial intelligence models and promoting open-source collaboration. It provides a platform for developers to contribute to and build applications using their foundational model, Stable Diffusion XL. They are pushing the boundaries in audio diffusion to generate high-quality music and sound effects, and they maintain a commitment to open access language models, competing with industry leaders. Stability AI has also developed the first open generative AI video model based on their image model. They emphasize community involvement and offer updates through a newsletter subscription.

Stability AI

Stability AI offers the Stable Diffusion model for images, audio, and language.

Stable Diffusion Launch by Stability AI

Recent Product News