Shypd.aiThe largest open index of AI toolsSa2VA is a computer vision tool that provides dense grounded understanding of images and videos. It combines SAM2 with LLaVA to support a wide range of image and video tasks, including referring segmentation and conversation.
Trending
About
Sa2VA is an open-source codebase for Pixel-LLM, designed for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, which are often limited to specific modalities and tasks, Sa2VA supports a wide range of image and video tasks, including referring segmentation and conversation, with minimal one-shot instruction tuning. It achieves this by combining SAM-2, a foundation video segmentation model, with LLaVA, an advanced vision-language model, unifying text, image, and video into a shared LLM token space. The repository provides various models, training code, inference capabilities, and evaluation scripts for different benchmarks.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
