wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-04-15 04:52:31 +08:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity

Fix noise/latent tensor mismatch when latent is nested but noise is not

Browse Source 
When using LTXAV (audio+video) workflows, latent_image is a NestedTensor
but noise may be a regular tensor. Calling unbind() on non-nested noise
splits along dim=0 (channels), producing a shape mismatch at noise_scaling.

Check whether noise is nested before unbinding. If not, pad with zero-noise
for additional components (e.g. audio), which is semantically correct since
those components don't need denoising in the video sampler.
This commit is contained in:
Dustin 2026-04-07 06:07:26 -04:00
parent b615af1c65
commit 2beca418ad
No known key found for this signature in database
GPG Key ID: CD4385E7B7BA3529
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
comfy/samplers.py
View File

@ -1006,8 +1006,16 @@ class CFGGuider:
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:
n_tensors = noise.unbind()
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]