Features
Real-time video generation at 25 fps
Keyboard and mouse input control
Auto-regressive diffusion-based image-to-world framework
Long video generation with temporal coherence
Open-source code and models (MIT license)
Three pretrained scenes: universal, GTA driving, TempleRun
Demo utilities and configuration files
Hugging Face model integration
Local inference on Linux with NVIDIA GPU
Text-to-image generation via REST API
Text-to-audio generation via REST API
Text-to-video generation via REST API
Text generation from prompts via API
No registration required for API access
Play area for experimentation
App library with usage examples
Cross-platform API access
Customizable generation parameters
Free tier with no explicit usage limits
Open-source model availability
Multi-modal support (image, audio, video, text)
Browser-based web interface
