Awesome, I'd love to see a video about how high-fidelity VAEs work and how they're trained.
@oblivitus.Ай бұрын
Brilliant! thank you!!
@soroushmehrabanАй бұрын
@@oblivitus. Thanks for watching
@HassanHamidi-v8s3 ай бұрын
Wow! great video. thanks a lot.
@soroushmehraban3 ай бұрын
@@HassanHamidi-v8s Thanks for watching it 🙂
@vidaadelimosabeb66893 ай бұрын
Great video, keep it up!
@soroushmehraban3 ай бұрын
@@vidaadelimosabeb6689 Thanks😃
@WaltonBoyd-c8g28 күн бұрын
Ariane Gateway
@moeinshariatnia592 ай бұрын
at 5:58 " ... the variance comes from the network" This is not right. In DDPM, the authors made it constant and then in later studies people started to make those learnable as well.
@soroushmehraban2 ай бұрын
@@moeinshariatnia59 In that formulation it is. Later in video I mentioned that it’s not necessary and model has to only predict the noise sampled from zero mean unit variance.
@moeinshariatnia592 ай бұрын
@@soroushmehraban It's so funny you delete the comment instead of correcting the mistake :))
@soroushmehraban2 ай бұрын
@@moeinshariatnia59 I didn't delete anything. It wasn't a mistake. Sorry if my explanation was ambiguous.