Be-a-Warior

IndexError: The shape of the mask [0] at index 0 does not match the shape of the indexed tensor [1, 4096, 320] at index 0

4

Hello, during the stage_1 of training, there was a dimension mismatch issue during the first validation set validation after training 200 steps.

Does it support multi-resolution inference

1

Does the current open-source 512 model support generating videos of other resolutions without the need for retraining