Detailed captions, object detection, segmentation, and visual question answering.
Image Understanding Capabilities
Document Analysis
Upload invoices, receipts, contracts, or any document.
Extract structured data.
Supports all pre-built document domains, including invoices, receipts, forms, and more.
Document Analysis in Chat Playground
Video Generation
Edit and generate images and videos from text prompts or images.
Image-to-Video Generation Features
Multi-Modal Conversations
Combine text, images, and structured data.
Ask follow-up questions or request modifications.