1 code implementation • 25 Mar 2022 • Louay Hazami, Rayhane Mama, Ragavan Thurairatnam
We present simple modifications to the Very Deep VAE to make it converge up to $2. 6\times$ faster, save up to $20\times$ in memory load and improve stability during training.
Ranked #1 on Image Generation on FFHQ 1024 x 1024 (bits/dimension metric)