CogVideo: Large-Scale Pretraining for Text-to-Video Generation via Transformers

Re:CogVideo: Large-Scale Pretraining for Text-to-Video Gener... by jimmygrapes on Monday May 30, 2022 @06:37PM (#31564381)

Unless compute costs drop to near free, it will always be cheaper to pay some desperate and/or "liberated" woman a few USD to do such things.

[ Parent | on HN ]

Re:CogVideo: Large-Scale Pretraining for Text-to-Video Gener... by Teever on Monday May 30, 2022 @06:42PM (#31564427)

That was the old porn paradigm.

I think you're unaware of just how much some people make on onlyfans. It's far more than a few dollars.

not to mention something like this will allow you to generate body types that are very rare, if not outright impossible, and you can animate them doing things that are also very rare, or outright impossible.

[ Parent | on HN ]

Re:CogVideo: Large-Scale Pretraining for Text-to-Video Gener... by azinman2 on Tuesday May 31, 2022 @01:20AM (#31566349)

Key is some. It’s a Pareto distribution.

Perhaps synthetic porn will get there some day. But we’re far off from being able to do consistent scenes and the tools to create them.

[ Parent | on HN ]