The CausVid generative AI tool uses a diffusion model to teach an autoregressive (frame-by-frame) system to rapidly produce stable, high-resolution videos.
Hybrid AI model crafts smooth, high-quality videos in seconds
Submitted 1 day ago by Pro@programming.dev to technology@lemmy.zip
https://news.mit.edu/2025/causevid-hybrid-ai-model-crafts-smooth-high-quality-videos-in-seconds-0506
A_A@lemmy.world 1 day ago
Arguably about 100 fold improvement over "diffusion models” like OpenAl’s SORA and Google’s VEO 2.
Such major improvements are to be expected in my opinion in the future of artificial intelligence.