search

hotshotco / Hotshot-XL

✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL
https://hotshot.co
Apache License 2.0
982 stars 77 forks source link

EinopsError: #32

Closed XTRMsavage closed 7 months ago

XTRMsavage commented 7 months ago

HI, When I am trying to do the following I am getting the error below. How to resolve it?

Error while processing rearrange-reduction pattern "(b f) c h w -> b c f h w". Input tensor shape: torch.Size([2, 320, 8, 64, 64]). Additional info: {'b': 2}. Expected 4 dimensions, got 5

image image
Zyablik1989 commented 7 months ago

HI, When I am trying to do the following I am getting the error below. How to resolve it?

Error while processing rearrange-reduction pattern "(b f) c h w -> b c f h w". Input tensor shape: torch.Size([2, 320, 8, 64, 64]). Additional info: {'b': 2}. Expected 4 dimensions, got 5

I got the same thing. It's happen because you have no SDXL model in memory.

It's either when you just restarted A1111 and didn't generated a single (non-animated) image, or when you tried to generate a gif, but got a CUDA outOfMemoryError and SDXL model went unloaded