Scroll down and there are more videos --- seems like models will be there "soon".

There's a 5 second version available: https://huggingface.co/Efficient-Large-Model/SANA-Video_2B_7...

> SANA-WM uses only ~213K public video clips with metric-scale pose supervision, completes training in 15 days on 64 H100s, and generates each 60-second clip on a single GPU; its distilled variant runs on a single RTX 5090 with NVFP4 quantization to denoise a 60s 720p clip in 34s.