Have you seen the one of SpongeBob driving off
Have you seen the one of SpongeBob driving off![]()
No I didn’t. would you show me?
![]()
I wonder how they get the data to replicate these dashcam videos. AI primarily copies so are open ai using youtube videos![]()
Yes but they still need reference material, and a whole bunch of it, to basically do the generation. Allot of these models are just scaled (more training data) . They can’t generate something they’ve never seen.It a new A.I prompt called Sora A.I 2
This one is a higher upgrade from the previous one called Sora A.I 1
- chatgpt not being able to generate images of full wine glassesIt’s about understanding how image generators work. They can morph many images together, but they always rely on the data they were trained on.
A typical wine glass, like the ones you find in every restaurant, is usually never filled to the brim because you can’t drink from such a glass without spilling everything. Prestige and theater has a price… (And the wine needs to breathe too. The pore wine was sooo long locked in the bottle.) However, a mug is usually filled to the top. But a mug is not a typical wine glass.![]()
Yes but they still need reference material, and a whole bunch of it, to basically do the generation. Allot of these models are just scaled (more training data) . They can’t generate something they’ve never seen.
- chatgpt not being able to generate images of full wine glasses
what i’m trying to get at is how did they get this data![]()