Defensively truncate/pad nested noise components to match latent

When noise.is_nested with a different number of components than
latent_image, truncate extras or pad missing components with
torch.zeros_like, mirroring the denoise_mask handling pattern below.

Addresses CodeRabbit nitpick on #13318.
This commit is contained in:
Dustin 2026-05-03 23:52:08 -04:00
parent 2beca418ad
commit 0388ac4309
No known key found for this signature in database
GPG Key ID: CD4385E7B7BA3529

View File

@ -1008,7 +1008,10 @@ class CFGGuider:
if latent_image.is_nested:
li_tensors = latent_image.unbind()
if noise.is_nested:
n_tensors = noise.unbind()
# Truncate extra noise components, pad missing ones with zeros
n_tensors = list(noise.unbind()[:len(li_tensors)])
for i in range(len(n_tensors), len(li_tensors)):
n_tensors.append(torch.zeros_like(li_tensors[i]))
else:
# Noise only covers video -- pad remaining components (audio) with zeros
n_tensors = [noise]