In-browser image background removal

Generate interactive React app data visualizations

Generate text from images and prompts

View how beam search decoding works, in detail!

Display visual document retrieval leaderboard

Generate protein sequences that fit a given structure

Scrape and summarize web content

An end-to-end (e2e) Voice Language Model by Fish Audio.

Interpret and execute code with responses

Need to analyze data? Let a Llama-3.1 agent do it for you!

Generate realistic talking video from an image and audio

Run a web interface for text generation

Generate an edited image based on text instructions

Generate a talking-head video from an image and audio

Convert text to speech with customizable models and speakers

Create 3D mesh by chatting.

Generate text responses using images and text prompts

Describe objects in webcam feed

In-browser WebGPU background removal

Radiology Image & Report Explainer Demo. Built with MedGemma