This log will focus on Text to Video.

Navigation

Return to the Moon 🌙

https://civitai.red/articles/27881/hhhunters-logbook-02-moon-overview

Text to Video ( t2v )

What we can learn when there is no input image to guide the result.

To me, t2v is not the most controlled technique out there ...
But it is still a very interesting one !

It lets me observe how a video model reacts on its own :

• how it handles motion,

• how it interprets prompts,

• what kind of visual language it seems to understand best,

• and where its limits show up first.

I don't see this as a " final production " tool yet ... More like a test bench.

A good way to study the model,

understand how it " thinks ",

and gather useful clues for more controlled workflows later ( i2v ).

Work in progress ...