use cross attention for conditioning unet based on image embedding tokens (which opens up the door on conditioning on text encodings as well

This commit is contained in:
Phil Wang
2022-04-14 10:10:04 -07:00
parent 95b018374a
commit 68e9883f59
3 changed files with 124 additions and 44 deletions

View File

@@ -10,7 +10,7 @@ setup(
'dream = dalle2_pytorch.cli:dream'
],
},
version = '0.0.10',
version = '0.0.11',
license='MIT',
description = 'DALL-E 2',
author = 'Phil Wang',