successfully did some basic math and clipped the predicted x0 intermediate for the continuous time case

denoising_diffusion_pytorch/continuous_time_gaussian_diffusion.py

@@ -187,7 +187,7 @@ class ContinuousTimeGaussianDiffusion(nn.Module):
             # in Imagen, this was changed to dynamic thresholding
             x_start.clamp_(-1., 1.)
 
-            model_mean = alpha_next * (x * (1 - c) / alpha + c * x_start)
+            model_mean = alpha_next / alpha * x * (1 - c) + alpha_next * c * x_start
         else:
             model_mean = alpha_next / alpha * (x - c * sigma * pred_noise)
 

setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'denoising-diffusion-pytorch',
   packages = find_packages(),
-  version = '0.17.6',
+  version = '0.17.5',
   license='MIT',
   description = 'Denoising Diffusion Probabilistic Models - Pytorch',
   author = 'Phil Wang',