Stability AI Launches Japanese InstructBLIP Alpha

Sep 1st, 2023Product
  • 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.