Detect objects in images

Transform casual videos into 3D portraits

Explore token probability distributions with sliders

Create 3D models from images or video

Create 3D portraits from casual videos

Detect fraudulent Ethereum transactions

Generate images from text descriptions

Generate speech from text

Calculate FOB USD price based on inputs

Transform text to speech in multiple languages

Upload images to detect and map building damage

Run a dynamic script from an environment variable

Convert text to emojis or emojis to text

Edit images based on source and target prompts

Transform casual videos into free-viewpoint portraits

Generate talking face video from image and audio

Evaluate RAG systems with visual analytics

Decode images to teacher model outputs

View and submit LLM benchmark evaluations

Segment objects in images and videos using text prompts