Method__init__(self,
model_type='t2v',
patch_size=(1, 2, 2),
text_len=512
models/transformer/wan/modules/t2m_model.py:515
Functionattention(
q,
k,
v,
q_lens=None,
k_lens=None,
dropout_p=0.,
softmax_scale=None,
q_scale
models/transformer/wan/modules/tm2m_model.py:164
Functionattention(
q,
k,
v,
q_lens=None,
k_lens=None,
dropout_p=0.,
softmax_scale=None,
q_scale
models/transformer/wan/modules/attention.py:133
Functionattention(
q,
k,
v,
q_lens=None,
k_lens=None,
dropout_p=0.,
softmax_scale=None,
q_scale
models/transformer/wan/modules/t2m_model.py:163
Methodforward x: [B, L1, C]. context: [B, L2, C] or None. mask: [B, L2] or [B, L1, L2] or None.
models/transformer/wan/modules/t5.py:86
Methodforward(
self,
x,
e,
seq_lens,
freqs,
context,
contex
models/transformer/wan/modules/tm2m_model.py:382
Methodforward x: motion latents of shape [B, T, C]. x_mask: mask of shape [B, T], 1 for valid, 0 for invalid. t:
models/transformer/wan/modules/tm2m_model.py:650
Methodforward(
self,
x,
e,
seq_lens,
freqs,
context,
context_lens,
models/transformer/wan/modules/t2m_model.py:421
Methodforward x: motion latents of shape [B, T, C]. x_mask: mask of shape [B, T], 1 for valid, 0 for invalid. t:
models/transformer/wan/modules/t2m_model.py:602