Skip to content

Fix DDIMParallelScheduler batch path ignoring final_alpha_cumprod #14216

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

Open
Osamaali313 wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −2
Open

Fix DDIMParallelScheduler batch path ignoring final_alpha_cumprod #14216

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions src/diffusers/schedulers/scheduling_ddim_parallel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -282,7 +282,7 @@ def _get_variance(self, timestep: int, prev_timestep: int | None = None) -> torc
def _batch_get_variance(self, t: torch.Tensor, prev_t: torch.Tensor) -> torch.Tensor:
alpha_prod_t = self.alphas_cumprod[t]
alpha_prod_t_prev = self.alphas_cumprod[torch.clip(prev_t, min=0)]
alpha_prod_t_prev[prev_t < 0] = torch.tensor(1.0)
alpha_prod_t_prev[prev_t < 0] = self.final_alpha_cumprod
beta_prod_t = 1 - alpha_prod_t
beta_prod_t_prev = 1 - alpha_prod_t_prev

Expand Down Expand Up @@ -577,7 +577,7 @@ def batch_step_no_noise(
self.final_alpha_cumprod = self.final_alpha_cumprod.to(model_output.device)
alpha_prod_t = self.alphas_cumprod[t]
alpha_prod_t_prev = self.alphas_cumprod[torch.clip(prev_t, min=0)]
alpha_prod_t_prev[prev_t < 0] = torch.tensor(1.0)
alpha_prod_t_prev[prev_t < 0] = self.final_alpha_cumprod

beta_prod_t = 1 - alpha_prod_t

Expand Down
Loading