298977887/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-01-11 02:15:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Only calculate randn in some samplers when it's actually being used.

Browse Source
This commit is contained in:
comfyanonymous 2023-07-17 10:11:08 -04:00
parent ee8f8ee07f
commit 3a150bad15
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
comfy/k_diffusion/sampling.py
View File

@ -131,9 +131,9 @@ def sample_euler(model, x, sigmas, extra_args=None, callback=None, disable=None,
s_in = x.new_ones([x.shape[0]])
for i in trange(len(sigmas) - 1, disable=disable):
gamma = min(s_churn / (len(sigmas) - 1), 2 ** 0.5 - 1) if s_tmin <= sigmas[i] <= s_tmax else 0.
eps = torch.randn_like(x) * s_noise
sigma_hat = sigmas[i] * (gamma + 1)
if gamma > 0:
eps = torch.randn_like(x) * s_noise
x = x + eps * (sigma_hat ** 2 - sigmas[i] ** 2) ** 0.5
denoised = model(x, sigma_hat * s_in, **extra_args)
d = to_d(x, sigma_hat, denoised)
@ -172,9 +172,9 @@ def sample_heun(model, x, sigmas, extra_args=None, callback=None, disable=None,
s_in = x.new_ones([x.shape[0]])
for i in trange(len(sigmas) - 1, disable=disable):
gamma = min(s_churn / (len(sigmas) - 1), 2 ** 0.5 - 1) if s_tmin <= sigmas[i] <= s_tmax else 0.
eps = torch.randn_like(x) * s_noise
sigma_hat = sigmas[i] * (gamma + 1)
if gamma > 0:
eps = torch.randn_like(x) * s_noise
x = x + eps * (sigma_hat ** 2 - sigmas[i] ** 2) ** 0.5
denoised = model(x, sigma_hat * s_in, **extra_args)
d = to_d(x, sigma_hat, denoised)
@ -201,9 +201,9 @@ def sample_dpm_2(model, x, sigmas, extra_args=None, callback=None, disable=None,
s_in = x.new_ones([x.shape[0]])
for i in trange(len(sigmas) - 1, disable=disable):
gamma = min(s_churn / (len(sigmas) - 1), 2 ** 0.5 - 1) if s_tmin <= sigmas[i] <= s_tmax else 0.
eps = torch.randn_like(x) * s_noise
sigma_hat = sigmas[i] * (gamma + 1)
if gamma > 0:
eps = torch.randn_like(x) * s_noise
x = x + eps * (sigma_hat ** 2 - sigmas[i] ** 2) ** 0.5
denoised = model(x, sigma_hat * s_in, **extra_args)
d = to_d(x, sigma_hat, denoised)