I really don’t get why more people aren’t playing around with AI video, considering how cheaply you can just conjure something out of nothing. Today’s experiment is, can I make a fake 80s sitcom? The biggest challenge on this was the laugh track. If I prompted the AI for the laugh track, it had them laugh along with it. Instead, I had to prompt them to stand there awkwardly for a few seconds and then added in the laugh track afterward (generated by ElevenLabs).
I’m trying to see how I can push this building toward doing something longer in AI. Theoretically, a lengthy dialogue is perfectly possible as long as I have wide and close-ups to cut between (current limitation is 8s per cut if I want to use Veo 3 with sound).
Share this post