more attention

README.md

@@ -827,6 +827,7 @@ Once built, images will be saved to the same directory the command is invoked
 - [ ] train on a toy task, offer in colab
 - [ ] think about how best to design a declarative training config that handles preencoding for prior and training of multiple networks in decoder
 - [ ] extend diffusion head to use diffusion-gan (potentially using lightweight-gan) to speed up inference
+- [ ] bring in cross-scale embedding from iclr paper https://github.com/lucidrains/vit-pytorch/blob/main/vit_pytorch/crossformer.py#L14
 
 ## Citations
 

dalle2_pytorch/dalle2_pytorch.py

@@ -1064,7 +1064,7 @@ class Unet(nn.Module):
         dim_mults=(1, 2, 4, 8),
         channels = 3,
         attn_dim_head = 32,
-        attn_heads = 8,
+        attn_heads = 16,
         lowres_cond = False, # for cascading diffusion - https://cascaded-diffusion.github.io/
         sparse_attn = False,
         sparse_attn_window = 8,  # window size for sparse attention

setup.py

@@ -10,7 +10,7 @@ setup(
       'dream = dalle2_pytorch.cli:dream'
     ],
   },
-  version = '0.0.86',
+  version = '0.0.87',
   license='MIT',
   description = 'DALL-E 2',
   author = 'Phil Wang',