Stability AI officially announces the public release of the Stable Diffusion model with a broad response and ongoing efforts for safe and ethical usage.
The model is launched with a Creative ML OpenRAIL-M license permitting both commercial and non-commercial use, emphasizing the ethical and legal responsibilities of users.
An AI-based Safety Classifier is included to filter out undesired outputs, with parameters adjustable by the community for continual improvement.
The recommended model (v1.4 470k) requires 6.9 GB of VRAM; optimizations for broader chipset compatibility and further enhancements are in the pipeline.
Stability AI encourages ethical use of the technology and invites community contributions to improve its performance and discourse.

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 AI Goes Public

Recent Product News