From 9ec8d27217e11e575a779a444df5c8ff9ae49b5c Mon Sep 17 00:00:00 2001
From: Phil Wang <lucidrains@gmail.com>
Date: Wed, 31 Aug 2022 07:36:19 -0700
Subject: [PATCH] 0.27.7

---
 .../denoising_diffusion_pytorch.py            | 29 ++++++++++---------
 setup.py                                      |  2 +-
 2 files changed, 16 insertions(+), 15 deletions(-)

diff --git a/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py b/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
index b3854c0..cfae2e6 100644
--- a/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
+++ b/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
@@ -570,7 +570,7 @@ class GaussianDiffusion(nn.Module):
 
         times = torch.linspace(-1, total_timesteps - 1, steps=sampling_timesteps + 1)   # [-1, 0, 1, 2, ..., T-1] when sampling_timesteps == total_timesteps
         times = list(reversed(times.int().tolist()))
-        time_pairs = list(zip(times[:-1], times[1:]))  # [(T-1, T-2), (T-2, T-3), ..., (1, 0), (0, -1)]
+        time_pairs = list(zip(times[:-1], times[1:])) # [(T-1, T-2), (T-2, T-3), ..., (1, 0), (0, -1)]
 
         img = torch.randn(shape, device = device)
 
@@ -584,20 +584,21 @@ class GaussianDiffusion(nn.Module):
             if clip_denoised:
                 x_start.clamp_(-1., 1.)
 
-            if time_next > -1:
-                alpha = self.alphas_cumprod[time]
-                alpha_next = self.alphas_cumprod[time_next]
-
-                sigma = eta * ((1 - alpha / alpha_next) * (1 - alpha_next) / (1 - alpha)).sqrt()
-                c = (1 - alpha_next - sigma ** 2).sqrt()
-
-                noise = torch.randn_like(img)
-
-                img = x_start * alpha_next.sqrt() + \
-                      c * pred_noise + \
-                      sigma * noise
-            else:
+            if time_next < 0:
                 img = x_start
+                continue
+
+            alpha = self.alphas_cumprod[time]
+            alpha_next = self.alphas_cumprod[time_next]
+
+            sigma = eta * ((1 - alpha / alpha_next) * (1 - alpha_next) / (1 - alpha)).sqrt()
+            c = (1 - alpha_next - sigma ** 2).sqrt()
+
+            noise = torch.randn_like(img)
+
+            img = x_start * alpha_next.sqrt() + \
+                  c * pred_noise + \
+                  sigma * noise
 
         img = unnormalize_to_zero_to_one(img)
         return img
diff --git a/setup.py b/setup.py
index 414f322..ba5b1e8 100644
--- a/setup.py
+++ b/setup.py
@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'denoising-diffusion-pytorch',
   packages = find_packages(),
-  version = '0.27.6',
+  version = '0.27.7',
   license='MIT',
   description = 'Denoising Diffusion Probabilistic Models - Pytorch',
   author = 'Phil Wang',