MirageLSD: The First Live-Stream Video Diffusion Model (∞-Generation, 0-Latency)

MirageLSD: The First Live-Stream Video Diffusion Model (∞-Generation, 0-Latency)(mirage.decart.ai)

9 points by dnnssl2 304 days ago | 9 comments

dnnssl2 304 days ago |

MirageLSD: The First Live-Stream Diffusion (LSD) Model - A Vid2Vid running in real time, infinite generation, zero latency. Available now in a live-hosted unlimited demo at https://mirage.decart.ai!

Please check out our Wired article on this model: https://www.wired.com/story/decart-artificial-intelligence-m...

dapper_bison17 304 days ago | |

Looks sick! Is the goal to make a set of models that would allow for complete immersive VR/AR? Like Ready-Player-One vibes?

assembly_wizard 304 days ago |

Can you imagine vibe-coding a game in seconds and making it look triple-A in real-time?

Moishey-h 304 days ago |

Wow looks great Good work decart. Ai

axrsbn 304 days ago |

I tried it, this is so amazing!

dordots2 304 days ago |

Wow so exciting, new world !

hleihil1 303 days ago |

So exciting מדהים

countfeng 304 days ago |

So cool

infoshoc 304 days ago |

Holy cow