Skip to content

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.

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

Merged
patrickvonplaten merged 3 commits into from
Oct 5, 2022
Merged

Avoid negative strides for tensors #717

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1beb12d
Avoid negative strides for tensors
shirayu Oct 4, 2022
7f567ec
Changed not to make torch.tensor
shirayu Oct 4, 2022
dca59b8
Removed a needless copy
shirayu Oct 5, 2022
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
7 changes: 2 additions & 5 deletions src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -281,12 +281,9 @@ def __call__(
latents = init_latents

t_start = max(num_inference_steps - init_timestep + offset, 0)
timesteps = self.scheduler.timesteps[t_start:]

# Some schedulers like PNDM have timesteps as arrays
# It's more optimzed to move all timesteps to correct device beforehand
timesteps_tensor = torch.tensor(self.scheduler.timesteps[t_start:], device=self.device)

for i, t in enumerate(self.progress_bar(timesteps_tensor)):
for i, t in enumerate(self.progress_bar(timesteps)):
t_index = t_start + i

# expand the latents if we are doing classifier free guidance
Expand Down
7 changes: 2 additions & 5 deletions src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -315,12 +315,9 @@ def __call__(
latents = init_latents

t_start = max(num_inference_steps - init_timestep + offset, 0)
timesteps = self.scheduler.timesteps[t_start:]

# Some schedulers like PNDM have timesteps as arrays
# It's more optimzed to move all timesteps to correct device beforehand
timesteps_tensor = torch.tensor(self.scheduler.timesteps[t_start:], device=self.device)

for i, t in tqdm(enumerate(timesteps_tensor)):
for i, t in tqdm(enumerate(timesteps)):
t_index = t_start + i
# expand the latents if we are doing classifier free guidance
latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
Expand Down