ictnlp/LLaVA-Mini

LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.

2 best points · 2 comments · 1 Hacker News post · 573 GitHub stars · View on GitHub

Hacker News discussions

• LLaVA-Mini: Efficient Image and Video Large Multimodal Models (2 points, 2 comments, by Vily, 2025-01-13)