PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
GNU Affero General Public License v3.0
1.44k
stars
67
forks
source link
*** TypeError: PixArtAlphaCombinedTimestepSizeEmbeddings object argument after ** must be a mapping, not NoneType #126
Open
nighting0le01 opened 3 days ago
*** TypeError: PixArtAlphaCombinedTimestepSizeEmbeddings object argument after ** must be a mapping, not NoneType
what resolution and aspect ratio to pass in the added_cond_kwargs for transformer input of 1x4x128x128