You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- the videos were slop. the best image to video model i had available for actual use programatically was stable video diffusion and it only output ~4-5s for each image at very low resolutions.
16
+
- eventually i gave up on image to video completely as the videos were too low res for the algorithm to like
17
+
- shorts are better than full videos if you want algorithmic pull.
18
+
- subtitles are very important. shorts with subtitles do much better than shorts without them.
19
+
- the amount of views you need to make money off of youtube is kind of insane. as far as i understand,
20
+
youtube doesn't count views that come from the shorts feed or from the home page feed for monetization. videos need to be really really good to make it.
21
+
- another thing i tried was a video with much more manual interference. i tried making a
22
+
rk narayan story in the style of [paperman](https://www.youtube.com/watch?v=XrqSF2OOz_M).
23
+
sadly, while it turned out reasonably, it took me a lot of time and i didn't really enjoy the process
24
+
enough to put more time into it.
25
+
- overall, my personal intuition is thinking about this as an artist is better than thinking about it
26
+
from a swe perspective. inevitably someone will use these models to make great art, it would be nice to be that person.
0 commit comments