Yoav HaCohen
Yoav HaCohen
Thanks for reporting this issue. We will fix this.
On Torch 2.7 you get an out-of-memory error: ``` RuntimeError: MPS backend out of memory (MPS allocated: 45.81 GB, other allocations: 1.70 MB, max allowed: 45.90 GB). Tried to allocate...
When generating the vid-to-vid output, are you using the same seed as the one used for the original video? Try using a different seed for the initial video generation and...
Adding new cross-attention layers is a valid option, but you’ll likely need to handle positional embeddings. The current cross-attention layers don’t use positional embeddings, so you might want to reference...
Our image-to-video conditioning is implemented as a temporal inpainting task, using a different timestep for the conditioning tokens, it doesn’t rely on cross-attention. If you want to apply a similar...
> it is ok, this is hard task, we got unworking svd too, seems video is harder to impelent in sd cpp, thank u for ur hard work let me...
What version of PyTorch are you using? It works well on my Mac with PyTorch 2.3
Yes, we working on this.
Do you mean making the constraints stricter?
Hi! Currently you can use FlowEdit and similar techniques for restyling/video to video inference. We're working on depth maps and other guidance options.