Issues
- 0
是否中稿?
#24 opened by JoshonSmith - 0
train code release?
#23 opened by JoshonSmith - 0
sam_agnostic.py 的输入数据是什么?
#22 opened by ohmydroid - 1
视频和衣服素材处理问题
#17 opened by xiyuxiaoxiao - 0
details about Image-video joint training
#21 opened by swzparker7 - 0
Evaluation on ViViD dataset
#20 opened by hungnguyen2611 - 0
unable to get good results
#19 opened by sahilshukla3003 - 0
question about evaluation metric
#18 opened by justinday123 - 3
能运行吗
#14 opened by xiyuxiaoxiao - 2
怎么看生成的和使用自己的数据
#15 opened by xiyuxiaoxiao - 0
- 4
evluateion in VVT dataset
#13 opened by xiaohaoChen - 4
Confuse about cross attention
#12 opened by XinZhang0526 - 2
vivid weights size
#11 opened by AIFSH - 1
Does this work with image inputs?
#7 opened by spenpal - 2
could someone give help, strange result
#10 opened by AIFSH - 0
When will your train code release?
#9 opened by onepeachbiubiubiu - 6
When will your code release?
#1 opened by 1015904089 - 3
- 0
UNet3DConditionModel: size mismatch for conv_in.weight: copying a param with shape torch.Size([320, 4, 3, 3]) from checkpoint, the shape in current model is torch.Size([320, 9, 3, 3]).
#6 opened by agsoft-lee - 1
When will your dataset release?
#4 opened by hungnguyen2611 - 0
- 2
Evaluation
#2 opened by hungnguyen2611