clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIP.

Justin N. M. Pinkney Chuan Li

Published in: CoRR (2022)

Keyphrases

denoising
pre trained
video clips
image denoising
text mining
data sets
image processing
training data
control signals
feature extraction
multiscale
small number
statistical model