LLaVA OneVision 2 8B Instruct [!IMPORTANT] 🌟 The core work on this project is led by Glint Lab. For an interactive online experience, visit ve2s.ai . A multimodal vision language model that handles single images, multi image, and video inputs, built on a Qwen3 8B language backbone with a OneVision style vision encoder. The model is distributed as a HuggingFace transformers checkpoint with custom code ( trust remote code=True ). Requirements Base (image + frame sampling video) Optional: codec video backend The model ships a second video backend ( video backend="codec" ) that replaces uniform frame sampling with codec aware canvas packing driven by motion vectors and bit cost — typically yielding stronger long video accuracy at the same token budget. To enable it you need two extra pieces: ffmpeg version: ffmpeg 4.4.x – 7.x is recommended. The codec backend additionally needs POSIX flock (already present on Linux/macOS) for the on disk result cache, and roughly 2 GB free disk under $ONLINE CODEC CACHE DIR (defaults to $HF HOME/online codec ) per processed video. Quick start The repository ships a ready to run demo inference.py that covers both image and video paths. Programmatic use…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy