张宏伦

another question, in line 252-253 of main.py, you divide perc by percep_norm for normalization. how about substract percep_norm from perc, then divide the result by sqrt(var)?

I think boraturant means that the cropped videos may not follow the original aspect ratios.

@Amo5 这个是diffusers sdxl pipeline默认加的watermark ``` class NoWatermarker: def __init__(self): pass def apply_watermark(self, images: torch.FloatTensor): return images pipe = AutoPipelineForText2Image.from_pretrained(..., add_watermarker=False) pipe.watermark = NoWatermarker() ``` 这样就没了