dianyo

Using `torchsde.BrownianInterval` instead of `torchsde.BrownianTree` in class `BatchedBrownianTree`

2

**Is your feature request related to a problem? Please describe.** When I was doing some optimization for my pipeline, i found that the BrownianTree somehow took a bit more time....

Remove redundant comparison inside the diffusion loop of stable video diffusion pipeline

7

**Is your feature request related to a problem? Please describe.** I found that the inside the `__call__` of stable video diffusion keeps doing async memcpy between host to device as...

add weights_only argument for torch load to support new version of torch

2

## Motivation torch.load start raise error in newer version if not specify weights_only=False, where the default behavior is True. ## Modification - Update yapf using newer version to avoid `lib2to3`...

This modification will support multiple frames numpy array to be sent into ffmpeg pipe at once. The numpy array itself already native allocate the memory that we don't need call...