Visual Document Retrieval
π
2
Demo for multimodal embedding models
Edit a photo to match a new text description
Detect objects in images or videos
Generate personalized images preserving your face identity
Swap faces between two images
Generate captions for music audio
Chat with an AI assistant using text and images
Create a custom story with characters and plot
BLIP2 (cutting edge image captioning) in π€transformers
Ask questions about any image