Find your next building block

A generated island-survival show with an ongoing story, character channels and viewer-directed choices.

An interactive world model that streams explorable 704 × 1280 video while you drive the camera with keyboard and mouse.

A developing hybrid architecture combining generative video world models with Roblox's structured multiplayer engine.

A research preview for steering generated audiovisual worlds through camera movement and text actions.

An Interface World Model that synthesises an application interface frame by frame as a user interacts.

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.

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

A project page for a block-causal LTX-2.3 rebuild that generates joint audio and video in real time with mid-stream text instructions.

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.

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

Access MiniMax H3 clip generation through Venice's hosted interface and documented video API.

Vidpixo is an AI product video generator for e-commerce sellers. It turns product photos into shoppable videos, clones viral video styles, and creates AI product photos in one workspace.

An omni world model for spatial intelligence with pixel-perfect camera-controlled image and video generation.

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