First video with the guy walking the mountain in snow has consistency issues with the cave entrance. Which is "expected" at this model size?!
First video with the guy walking the mountain in snow has consistency issues with the cave entrance. Which is "expected" at this model size?!
My dreams have it too, which is unexpected at that model size!
Most videos seem to have some issues like that, e.g. the book on the table in the library video takes up different shapes every now and then.
The 'Refiner' effect seems to do the opposite if the examples are representative as in all cases the 1-st stage images look better than the 'refined' ones. Less clutter, more realistic, less 'cowbell' for those who know the phrase.
All of the videos have rather glaring consistency issues when direction shifts back to areas previously shown.
Remember the first Will Smith spaghetti?
Yeah it got ridiculed and people wrote it off as that was somehow the limit and that wasn't going to change which seems to be the common premise to which people launch their criticisms of AI
And those same people forget that its been 3 years since that awful will smith spaghetti video to what we have today which is the beginning of controllable real time videos aka games