> 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.
How does the archive they provide look like? Many zip files?
I would like to retrieve them and offload to another storage service but I don’t have local storage enough to hold all of it at the same time, unpack and then reupload. I would need to do it in stages.
Yes, many ZIP files. You can select the ZIP file sizes, from 1 to 25 GB, iirc. Although a few end up larger than 25 for some reason. And took 1-2 days for Apple to "prepare".
You can request a chunk size and then it prepares them. I specified max chunk size and it took almost a week to give me a list of file downloads from 45-60GB each. 31 zip files to download.
reply