AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

[UNet_Spatio_Temporal_Condition] fix default num_attention_heads in unet_spatio_temporal_condition (#7205)

Browse Source 
fix default num_attention_heads in unet_spatio_temporal_condition

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
This commit is contained in:
Xiaodong Wang
2024-03-09 12:29:06 +08:00
committed by GitHub
parent e3cd6cae50
commit 6f2b310a17
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/diffusers/models/unets/unet_spatio_temporal_condition.py
View File

@@ -90,7 +90,7 @@ class UNetSpatioTemporalConditionModel(ModelMixin, ConfigMixin, UNet2DConditionL
layers_per_block: Union[int, Tuple[int]] = 2,
cross_attention_dim: Union[int, Tuple[int]] = 1024,
transformer_layers_per_block: Union[int, Tuple[int], Tuple[Tuple]] = 1,
num_attention_heads: Union[int, Tuple[int]] = (5, 10, 10, 20),
num_attention_heads: Union[int, Tuple[int]] = (5, 10, 20, 20),
num_frames: int = 25,
):
super().__init__()