Artifacts

Removes unwanted objects from a photo and upscales images using models that run in the browser.

Stable Diffusion that runs completely in the browser through WebGPU, with no server-side inference.

Generates and interpolates between short melodies and drum patterns using a variational autoencoder in the browser.

Play a few buttons and a neural net turns them into a full piano performance in your browser.

Transcribes piano audio into MIDI notes in the browser using the Onsets and Frames model.

Runs Microsoft's Florence-2 vision model in the browser for captioning, detection and OCR tasks.

Draw a few strokes and a Sketch-RNN model keeps drawing the object, with a model picker for subjects like birds.

Real-time captions for webcam video generated by an LFM2-VL model inside the browser.

Live webcam captioning and object tracking using a 450M vision-language model on WebGPU.

Text-to-image model running fully in the browser on WebGPU, per the Space description.

Captions an image with BLIP compiled to WebAssembly via Rust Candle.

In-browser video captioning with the 2B LFM3-VL model via WebGPU.

Drives a cartoon avatar in real time from your webcam using MediaPipe tracking.

Turns a sentence into emojis with a Gemma 3 270M model running on your device.