Discover & rankings

A Minecraft-specific interactive video world model with downloadable checkpoints and a local web demo.

Learn and reproduce the full pipeline for converting video diffusion backbones into interactive world models.

A hosted real-time conversational video model for adding live visual agents to applications.

A developer platform for deploying and streaming real-time generative-media and world-model sessions.

An open data, training and inference stack for building long-horizon interactive video world models.

Serve world models and multimodal generators with stateful sessions, distributed inference and WebRTC streaming.

Transform live camera or video streams with prompt, reference-image and touch-driven controls.

An open-source workspace for interactive video generation and editing, with a browser interface and a self-hosted FastVideo backend.

Run ComfyUI workflows on live video streams, with a browser interface and WebRTC transport.

Explore long-running autoregressive video generation and the infrastructure behind interactive streams.

A research baseline for streaming video generation that trains models on their own autoregressive outputs.

A self-hosted experiment turning YouTube chat into generated clips and a continuously replayed broadcast.

Transform webcam and screen frames with an accelerated diffusion pipeline for interactive visuals.

Build interactive video streams with a diffusion system designed for configurable GPU pipelines.

Study streaming video-to-video stylization with feature banks that reuse information from earlier frames.

A source-available tool for running interactive generative-video pipelines, with a non-commercial alpha licence.

A keyboard-controlled open-world research experience whose visuals and mechanics are generated by a world model.