Success
Eagle2-VL is a multi-modal LLM that can understand text, images and videos, and generate text
Note: you can upload images or videos!
This demo is based on moonshotai/Kimi-VL-A3B-Thinking & deepseek-ai/deepseek-vl2-small and extends it by adding support for video input.
moonshotai/Kimi-VL-A3B-Thinking
deepseek-ai/deepseek-vl2-small