Stability AI releases SDXL 1.0, an advanced open image generation model, improving upon the earlier 0.9 version.
Features of SDXL 1.0 include high-quality image generation in any art style, exceptional photorealism, better color, contrast, and simple language prompts for detailed outputs.
Architectural innovation with a large parameter count, consisting of a 3.5B base and a 6.6B pipeline, enables robust and efficient image generation suitable for consumer GPUs.
The model facilitates easy fine-tuning with less data wrangling and has several task-specific control features currently in beta for future enhancement.
SDXL 1.0 is accessible via multiple platforms like ClipDrop and DreamStudio, with its weights and source code available on GitHub, and also through API on Stability AI Platform and AWS platforms.

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 1.0 Image Model

Recent Product News