This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
alphaXiv
alphaxiv.org
did:plc:xqp2wfy2sz5m7n2mu322izo2
Step-Video-T2V Technical Report
Step-Video-T2V is a 30B-parameter text-to-video model that generates high-quality videos from English and Chinese prompts, using deep compression VAE for efficiency and DiT with Flow Matching for denoising. It outperforms existing models in video generation.
2025-02-22T21:08:18.673Z