Llava is a web-based application that enables users to chat with a vision-language model by uploading images and entering text prompts. It provides detailed responses based on both modalities, serving AI researchers and enthusiasts.
In the AI space, Llava takes a focused approach. It focuses on providing conversational AI that can understand and respond to both images and text prompts. Llava is a consumer product aimed at AI researchers. It is available for free. It runs on the web, and it can be self-hosted.
llava-hf builds and maintains Llava, and it first shipped in 2024. Key capabilities include image upload, text prompt, and vision-language chat.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do