bring in prediction of v objective, combining the findings from progressive distillation paper and imagen-video to the eventual extension of dalle2 to make-a-video

dalle2_pytorch/dalle2_pytorch.py

@@ -629,7 +629,7 @@ class NoiseScheduler(nn.Module):
 
     def calculate_v(self, x_start, t, noise = None):
         return (
-            extract(self.sqrt_alphas_cumprod, t, x_start.shape) * noise +
+            extract(self.sqrt_alphas_cumprod, t, x_start.shape) * noise -
             extract(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape) * x_start
         )
 

dalle2_pytorch/version.py

@@ -1 +1 @@
-__version__ = '1.11.0'
+__version__ = '1.11.1'