Idea of improvement
#11
by
Fabrice-TIERCELIN
- opened
Hi,
What about creating a model with reversed videos? The idea is to propose an AI that generates a video from an image that ends the video instead of being the first frame. It should be quite easy to do:
- Reverse the videos from the original dataset
- Train the model the same way
- Create a dedicated space that inverts the order of the generated images
Regards
That is very wise! I will do it!
That is very wise! I will do it!
Hi~, how about your current model perform?
Hi @ramonzero343 ,
Can you tell me how to do that?
It seems very very hard to get the original dataset...
Fabrice-TIERCELIN
changed discussion status to
closed