-
Notifications
You must be signed in to change notification settings - Fork 6.1k
Avoid negative strides for tensors #717
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.
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
Avoid negative strides for tensors #717
Conversation
The documentation is not available anymore as the PR was closed or merged. |
src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py
Outdated
Show resolved
Hide resolved
@shirayu my feeling was that the imge2img pipeline would work without the need to convert the scheduler's timesteps to a torch tensor. If you have a look, the |
while you are there you could fix the spelling of optimzed -> optimized and I believe the same would hold for the stable diffusion too? what would you say @anton-l ? |
src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py
Outdated
Show resolved
Hide resolved
Running all slow tests now - if they pass, we're good to go! |
Tests all pass -> merging! |
* Avoid negative strides for tensors * Changed not to make torch.tensor * Removed a needless copy
* Avoid negative strides for tensors * Changed not to make torch.tensor * Removed a needless copy
The original lines cause the following error for tensors.
The same operation is done here.
diffusers/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
Lines 253 to 258 in f1484b8
(Probably related to #551 )