mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2026-02-02 09:40:19 +08:00
wan-vae: implement zero pad fast path
The WAN VAE is also QWEN where it is used single-image. These convolutions are however zero padded 3d convolutions, which means the VAE is actually just 2D down the last element of the conv weight in the temporal dimension. Fast path this, to avoid adding zeros that then just evaporate in convoluton math but cost computation.
This commit is contained in:
parent
613eee564b
commit
ea9d6fab23
@ -28,6 +28,11 @@ class CausalConv3d(ops.Conv3d):
|
||||
cache_x = cache_list[cache_idx]
|
||||
cache_list[cache_idx] = None
|
||||
|
||||
if cache_x is None and x.shape[2] == 1:
|
||||
#Fast path - the op will pad for use by truncating the weight
|
||||
#and save math on a pile of zeros.
|
||||
return super().forward(x, autopad="causal_zero")
|
||||
|
||||
if self._padding > 0:
|
||||
padding_needed = self._padding
|
||||
if cache_x is not None:
|
||||
|
||||
Loading…
Reference in New Issue
Block a user