Stable Zero123 is an advanced model for view-conditioned image generation, outperforming prior models such as Zero123-XL with higher quality results.
The model benefits from an improved dataset, elevation conditioning during training, and an optimized dataloader, resulting in a 40X training efficiency increase.
Stable Zero123 is available on Hugging Face for non-commercial and research use, while Stable Zero123C is available for commercial use with a Stability AI membership.
The development includes updated threestudio open-source code for creating 3D objects and the process can be further used for text-to-3D generation.
Two versions of Stable Zero123 have been released, distinguishing non-commercial from commercial use, with similar performance in prediction quality.

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 Zero123: Enhanced 3D Object Generation

Recent Product News