From e839686bfcf72727f9e51a0c609e1d4d6a52c71f Mon Sep 17 00:00:00 2001
From: Mira Sato <275437409+oab24413gmai@users.noreply.github.com>
Date: Thu, 14 May 2026 04:22:46 +0000
Subject: [PATCH] docs: fix duplicated "to" in UNetSpatioTemporalConditionModel
 docstring

---
 src/diffusers/models/unets/unet_spatio_temporal_condition.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/diffusers/models/unets/unet_spatio_temporal_condition.py b/src/diffusers/models/unets/unet_spatio_temporal_condition.py
index eddeb9826b0c..0bad41fb250a 100644
--- a/src/diffusers/models/unets/unet_spatio_temporal_condition.py
+++ b/src/diffusers/models/unets/unet_spatio_temporal_condition.py
@@ -49,7 +49,7 @@ class UNetSpatioTemporalConditionModel(ModelMixin, AttentionMixin, ConfigMixin,
         block_out_channels (`tuple[int]`, *optional*, defaults to `(320, 640, 1280, 1280)`):
             The tuple of output channels for each block.
         addition_time_embed_dim: (`int`, defaults to 256):
-            Dimension to to encode the additional time ids.
+            Dimension to encode the additional time ids.
         projection_class_embeddings_input_dim (`int`, defaults to 768):
             The dimension of the projection of encoded `added_time_ids`.
         layers_per_block (`int`, *optional*, defaults to 2): The number of layers per block.