Vily

Stream-Omni is an GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across any modality combinations.

LLaVA-Mini👏is an efficient LMM for image/video understanding using 1 vision token, offering: (1)⏩fast response (40ms per image) (2)🖥️less VRAM usage (support 3-hour video understanding on 24GB GPU).