Stability AI released SDXL 0.9, an advanced AI model for realistic image generation, offering detailed composition improvement over previous versions.
SDXL 0.9 is compatible with consumer GPUs and offers functionalities like image-to-image prompting, inpainting, and outpainting.
With a 3.5B parameter base model and a 6.6B parameter pipeline, SDXL 0.9 utilizes two CLIP models, including OpenCLIP ViT-G/14, for high-resolution output.
Accessible on ClipDrop with future API access, SDXL 0.9 is available for researchers with an open release scheduled for mid-July.
Since its beta, the SDXL series has generated huge engagement with over 700,000 images created by the Discord community.

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.

Stability AI Introduces SDXL 0.9 for Enhanced AI Imagery

Recent Product News