MCPcopy Create free account
hub / github.com/OpenImagingLab/FlashVSR / __init__

Method __init__

diffsynth/models/wan_video_text_encoder.py:24–28  ·  view source on GitHub ↗
(self, dim, eps=1e-6)

Source from the content-addressed store, hash-verified

22class T5LayerNorm(nn.Module):
23
24 def __init__(self, dim, eps=1e-6):
25 super(T5LayerNorm, self).__init__()
26 self.dim = dim
27 self.eps = eps
28 self.weight = nn.Parameter(torch.ones(dim))
29
30 def forward(self, x):
31 x = x * torch.rsqrt(x.float().pow(2).mean(dim=-1, keepdim=True) +

Callers 5

__init__Method · 0.45
__init__Method · 0.45
__init__Method · 0.45
__init__Method · 0.45
__init__Method · 0.45

Calls

no outgoing calls

Tested by

no test coverage detected