Everything in the catalog

Translate text between a chosen pair of languages using the University of Helsinki OPUS models.

Hum a melody and have AI turn it into a finished song.

Generates a high-resolution 3D model from an input image with the Sparc3D model.

Generate videos that come with a synchronized soundtrack.

Super-resolution demo that sharpens and upscales a photo.

Classifies webcam frames against text labels you type, using Jina CLIP on WebGPU.

Play Mario, Rubik's Cube and Tetris with JEV-27B

Simple video, smart scenes, identity & efficient Turbo

Six-step video + audio · Pika reference code

Free text to a VLA through a VLM planner, in LeRobot

TTS for any emotion, now with non-verbal sounds!

Chess demo where the moves come from a simulated fruit fly brain.

Generates a high-fidelity 3D model from a single image.

Turns entered lyrics or a text prompt into a short generated music clip.

Fast Editing with Robust Consistency

Genshin Impact & Honkai Star Rail game character voice TTS

8-step DMD text-to-image distillation of MOSS-Image-SFT

Design proteins and complexes with RFD4-Proteína

Scene-text recognition using the PARSeq model.

Speech-to-text demo that transcribes microphone input with Whisper.

Estimates depth from a single image with Depth Anything running through WebGPU.

Use title and abstract to predict future academic impact

Multi-task image generator with dynamic, chainable workflows

Molmo2 - Image, Video (QA, Pointing & Tracking)