demo of batch processing with moondream

Ivy-VL is a lightweight multimodal model with only 3B.

Watch a video exploring AI, ethics, and Henrietta Lacks

Answer questions about documents and images

Select and visualize language family trees

Chat with documents like PDFs, web pages, and CSVs

Generate answers to questions about images

Rank images based on text similarity

Image captioning, image-text matching and visual Q&A.

Generate answers using images or videos

Analyze video frames to tag objects

Visualize 3D dynamics with Gaussian Splats

Turn your image and question into answers

Create visual diagrams and flowcharts easily

A private and powerful multimodal AI chatbot that runs local

Explore interactive maps of textual data

One-minute creation by AI Coding Autonomous Agent MOUSE-I"

Ask questions about images to get answers

Explore data leakage in machine learning models

Display sentiment analysis map for tweets