Stability-AI / generative-models

Generative Models by Stability AI
MIT License
24.44k stars 2.72k forks source link

How should I set the duration for generating a video use SVD? #182

Open biandh opened 11 months ago

biandh commented 11 months ago

I am running the scripts/sampling/simple_video_sample.py file

WyattSanders commented 11 months ago

I tried loading SVD but I get this error with svd_xt: \scripts\demo\video_sampling.py", line 142, in value_dict["cond_frames"] = img + cond_aug * torch.randn_like(img) TypeError: randn_like(): argument 'input' (position 1) must be Tensor, not NoneType

Cyclones-Y commented 11 months ago

I tried loading SVD but I get this error with svd_xt: \scripts\demo\video_sampling.py", line 142, in value_dict["cond_frames"] = img + cond_aug * torch.randn_like(img) TypeError: randn_like(): argument 'input' (position 1) must be Tensor, not NoneType

我和你的问题一样,但是这不影响程序的正常运行,只需将图片上传即可消除该报错。

Cyclones-Y commented 11 months ago

time = T/fps