Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Dedun, Vincent"'
Autor:
Deng, Yitong, Lin, Winnie, Li, Lingxiao, Smirnov, Dmitriy, Burgert, Ryan, Yu, Ning, Dedun, Vincent, Taghavi, Mohammad H.
Adapting pretrained image-based diffusion models to generate temporally consistent videos has become an impactful generative modeling research direction. Training-free noise-space manipulation has proven to be an effective technique, where the challe
Externí odkaz:
http://arxiv.org/abs/2411.01212
