Decart MirageLSD

Qu’est-ce que Decart MirageLSD ?

Decart's MirageLSD is a causal autoregressive diffusion model that transforms an incoming video stream in real time via text prompt, without the drift that broke earlier streaming models after ~20–30 seconds. It runs on Hopper-class GPUs with custom CUDA kernels and is offered through a Crusoe Cloud partnership; latency figures are vendor-reported ('under 40ms per frame') and not yet independently benchmarked. Karpathy is an angel investor and has called it 'real-time magic'.

Ce que fait Decart MirageLSD

• Causal autoregressive diffusion that restyles a live input feed frame-by-frame from a text prompt
• Avoids the error-accumulation collapse that killed earlier streaming models after ~20–30 seconds
• Runs on Hopper-class GPUs with custom CUDA kernels
• Available as an API through a Crusoe Cloud partnership
• Backed by notable angels including Andrej Karpathy, who has called it “real-time magic”

À qui s’adresse Decart MirageLSD ?

• Live video-to-video effects on a camera, game, call or screen feed
• Building realtime creative overlays without clip generation
• Studying causal live-diffusion as an alternative to autoregressive streaming models

Points forts et limites de Decart MirageLSD

Ce qu’on en dit

Citations issues de couverture publique — collectées le 2026-09-03.

Questions fréquentes