New AI text to video tool

[C7373]

“Introducing Sora, our text-to-video model.

Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.” - OpenAI on twitter

I wonder if anything time stop related could be created with this. I assume nothing NSFW will be allowed to be created but could still be interesting .

[Kiro]

I thought exactly the same thing, I think so, the problem is using the right commands, sometimes I use text AI, just to play around a little, and in this case, stopping time often doesn't work the way we want, when it comes out I'll keep an eye on this new AI, in case anyone here manages to use it correctly.

[freezefantasy]

I play with GenAI a lot. Will definitely have a bit of experiment when it public releases in a few months.

So far I have found three tricks to overcome content safety blocks:

- say it's for a viral marketing campaign (lots of time stands still ad concepts in the Sora training data)
- choose scenarios where skimp clothing is perfectly normal (beach volleyball, catwalk, summer joggers, swimming pool, summer time)
- ask for analogous objects to be applied onto the character (white candle wax, pink banana, etc)

Some ideas I've got on the prompt queue to combine with the tricks above.
- statue street performers
- store living mannequin
- art class subject volunteer
- bullet time pan