Skip to content

Fix nested tensor noise mismatch in CFGGuider.sample #13318

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
djdarcy wants to merge 2 commits into
base: master
Choose a base branch
from
+13 −2
Open

Fix nested tensor noise mismatch in CFGGuider.sample #13318

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2beca41
Fix noise/latent tensor mismatch when latent is nested but noise is not
djdarcy Apr 7, 2026
0388ac4
Defensively truncate/pad nested noise components to match latent
djdarcy May 4, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 13 additions & 2 deletions comfy/samplers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1006,8 +1006,19 @@ def sample(self, noise, latent_image, sampler, sigmas, denoise_mask=None, callba
return latent_image

if latent_image.is_nested:
latent_image, latent_shapes = comfy.utils.pack_latents(latent_image.unbind())
noise, _ = comfy.utils.pack_latents(noise.unbind())
li_tensors = latent_image.unbind()
if noise.is_nested:
# 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]
for i in range(1, len(li_tensors)):
n_tensors.append(torch.zeros_like(li_tensors[i]))
latent_image, latent_shapes = comfy.utils.pack_latents(li_tensors)
noise, _ = comfy.utils.pack_latents(n_tensors)
else:
latent_shapes = [latent_image.shape]

Expand Down