Skip to content

Open-Sora: Democratizing Efficient Video Production for All

Python

Commits on main

[wip] try vae
zhengzangw committed 2 years ago
b2f302b
Update README.md
fastalgo committed 2 years ago
ed04275
debug
Shen-Chenhui committed 2 years ago
da5f42d
debug
Shen-Chenhui committed 2 years ago
c584743
disable t-conv for t=1
Shen-Chenhui committed 2 years ago
e3b8424
add z nll loss
Shen-Chenhui committed 2 years ago
c631358
merged
zhengzangw committed 2 years ago
9632b5b
update
zhengzangw committed 2 years ago
5c81395
fix merge
Shen-Chenhui committed 2 years ago
b78b469
move out losses to different file
Shen-Chenhui committed 2 years ago
f81d864
update
zhengzangw committed 2 years ago
a2dc903
scenedetect installation guide
Tom Young committed 2 years ago
e84ccb2
clean up code
Shen-Chenhui committed 2 years ago
4d69671
config ablate lr
Shen-Chenhui committed 2 years ago
bd5ca0f
update config
zhengzangw committed 2 years ago
1171e5b
config
Shen-Chenhui committed 2 years ago
98de789
change frame interval
Shen-Chenhui committed 2 years ago
5de47c3
add config image to video
Shen-Chenhui committed 2 years ago
dec9248
add image inference pixabay
Shen-Chenhui committed 2 years ago
b028c9c
add Nlayer 3D discriminator
Shen-Chenhui committed 2 years ago
7811b8e
use 3 layer disc
Shen-Chenhui committed 2 years ago
069ffcc
complete 3b backbone
zhengzangw committed 2 years ago
f3dcb4d
train 100 epochs image
Shen-Chenhui committed 2 years ago
19477d9
add vae subfolder support
Shen-Chenhui committed 2 years ago
8b465b0
image train
Shen-Chenhui committed 2 years ago
c4318e9
add image support
Shen-Chenhui committed 2 years ago
73c6b19
config
Shen-Chenhui committed 2 years ago
6ea8998
latest inference script
Shen-Chenhui committed 2 years ago
ffc306c