Skip to content

Fix a bug for DDIM sampling #587

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
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix a bug for DDIM sampling #587

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
6 changes: 4 additions & 2 deletions ldm/modules/diffusionmodules/util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,9 @@ def make_ddim_timesteps(ddim_discr_method, num_ddim_timesteps, num_ddpm_timestep
def make_ddim_sampling_parameters(alphacums, ddim_timesteps, eta, verbose=True):
# select alphas for computing the variance schedule
alphas = alphacums[ddim_timesteps]
alphas_prev = np.asarray([alphacums[0]] + alphacums[ddim_timesteps[:-1]].tolist())

# alphas_prev should start with 1.
alphas_prev = np.append(1., alphas[:-1])

# according the the formula provided in https://arxiv.org/abs/2010.02502
sigmas = eta * np.sqrt((1 - alphas_prev) / (1 - alphas) * (1 - alphas / alphas_prev))
Expand Down Expand Up @@ -267,4 +269,4 @@ def forward(self, c_concat, c_crossattn):
def noise_like(shape, device, repeat=False):
repeat_noise = lambda: torch.randn((1, *shape[1:]), device=device).repeat(shape[0], *((1,) * (len(shape) - 1)))
noise = lambda: torch.randn(shape, device=device)
return repeat_noise() if repeat else noise()
return repeat_noise() if repeat else noise()