Vary-toy is a compact, open-source visual language model enabling document OCR, image description, visual question answering, and multimodal dialogue on consumer-grade hardware.
Llama 3.2 is Meta's open-weight multimodal model family optimized for edge devices, supporting vision-language understanding, on-device text generation, and customizable local deployment.
GenStoryBook uses AI to turn a simple prompt, photos, and artwork into a 10-page personalized picture book with illustrations, voice narration, and educational content.
SenseNova is SenseTime's multimodal foundation model family, available through an API for text, image, video and speech generation and reasoning tasks.
