More on Rife-App (Patreon)
Content
Ok, don't kill me, but while finishing the code for the app I kept training the model with some new tests, the test made a great improvement on the model, so I had to train it a little more.
But good news, it should be ready tomorrow. Even more good news, during this time I managed to train the RL model as well, so the next update will have both models.
RL model can still be improved, but for that, I need to make a new Dataset myself, so it will take a some time.
Here are two examples for the Animation model:
https://streamable.com/1diviq
https://streamable.com/lfv8g0
It still have some small problems, but it can handle edge cases a lot better than the older models.
And here two examples for the RL model.
I left "Perfect loop" turned on, to show that even in impossible interpolations, it don't look that bad.
Both are still in the last steps of training, so they should improve a little more before release.