You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have searched the existing issues and checked the recent builds/commits of both this extension and the webui
Have you read FAQ on README?
I have updated WebUI and this extension to the latest version
What happened?
einops.EinopsError: Error while processing rearrange-reduction pattern "(b f) d c -> (b d) f c".
Input tensor shape: torch.Size([2, 1369, 320]). Additional info: {'f': 8}.
Shape mismatch, can't divide axis of length 2 in chunks of 8
EinopsError: Error while processing rearrange-reduction pattern "(b f) d c -> (b d) f c". Input tensor shape: torch.Size([2, 1369, 320]). Additional info: {'f': 8}. Shape mismatch, can't divide axis of length 2 in chunks of 8
AnimateDiff is not running correctly.
First image created without AnimateDiff enabled > Enable AnimateDiff > Error > Disable AnimateDiff > Continued Error
If anyone has a workaround, please share.
WEB UI version is 1.6.0
Python 3.10.6
Steps to reproduce the problem
Go to ....
Press ....
...
First image created without AnimateDiff enabled > Enable AnimateDiff > Error > Disable AnimateDiff > Continued Error
What should have happened?
There should be no errors.
Commit where the problem happens
webui:
extension: AnimateDiff
What browsers do you use to access the UI ?
Microsoft Edge
Command Line Arguments
no
Console logs
no
Additional information
No response
The text was updated successfully, but these errors were encountered:
I've tried to get this to work, and have the problem with einops error.
"EinopsError: Error while processing rearrange-reduction pattern "(b f) d c -> (b d) f c". Input tensor shape: torch.Size([2, 4096, 320]). Additional info: {'f': 16}. Shape mismatch, can't divide axis of length 2 in chunks of 16"
I am only guessing it's the same as this, if not, I'm sorry, I don't know this stuff very well.
in any case, this problem then persists even if I no longer enable animatediff, and try to run regular prompts. Very strange behavior.
oh and I updated most things like twice, and I am trying out the various models available for animatediff to see if there's any difference, but nothing has been different so far.
Is there an existing issue for this?
Have you read FAQ on README?
What happened?
einops.EinopsError: Error while processing rearrange-reduction pattern "(b f) d c -> (b d) f c".
EinopsError: Error while processing rearrange-reduction pattern "(b f) d c -> (b d) f c". Input tensor shape: torch.Size([2, 1369, 320]). Additional info: {'f': 8}. Shape mismatch, can't divide axis of length 2 in chunks of 8
AnimateDiff is not running correctly.
First image created without AnimateDiff enabled > Enable AnimateDiff > Error > Disable AnimateDiff > Continued Error
If anyone has a workaround, please share.
WEB UI version is 1.6.0
Python 3.10.6
Steps to reproduce the problem
First image created without AnimateDiff enabled > Enable AnimateDiff > Error > Disable AnimateDiff > Continued Error
What should have happened?
There should be no errors.
Commit where the problem happens
webui:
extension: AnimateDiff
What browsers do you use to access the UI ?
Microsoft Edge
Command Line Arguments
Console logs
Additional information
No response
The text was updated successfully, but these errors were encountered: