Ruibin Li
LetsThink
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 19 hours ago
Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars updated a dataset about 2 months ago
LetsThink/tmp_save_latent published a dataset about 2 months ago
LetsThink/tmp_save_latentOrganizations
finetuning
10
#16 opened over 2 years ago
by 
hollowsense
About the training process
2
#5 opened over 2 years ago
by LetsThink
Use pretrain VAE to encode a 512x512 image to latent space get nan, the image has been normalized to [-1,1]
3
#10 opened over 3 years ago
by LetsThink