Stability AI has introduced a new vision-language model named Japanese InstructBLIP Alpha.
This model can generate textual descriptions from images and answer questions based on images.
It builds upon Japanese StableLM Instruct Alpha 7B and is fine-tuned using limited Japanese datasets for recognizing Japan-specific objects.
Examples of its application include search engines, scene descriptions & QA, and assisting visually impaired individuals.
The model is available for research purposes via the Hugging Face Hub.

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 Launches Japanese InstructBLIP Alpha

Recent Product News