Fix documentation typo for UNet2DModel and UNet2DConditionModel (huggingface#1275)

* Fix documentation typo

* Fix other typo

Author: xenova

src/diffusers/models/unet_2d.py

@@ -51,7 +51,7 @@ class UNet2DModel(ModelMixin, ConfigMixin):
         time_embedding_type (`str`, *optional*, defaults to `"positional"`): Type of time embedding to use.
         freq_shift (`int`, *optional*, defaults to 0): Frequency shift for fourier time embedding.
         flip_sin_to_cos (`bool`, *optional*, defaults to :
-            obj:`False`): Whether to flip sin to cos for fourier time embedding.
+            obj:`True`): Whether to flip sin to cos for fourier time embedding.
         down_block_types (`Tuple[str]`, *optional*, defaults to :
             obj:`("DownBlock2D", "AttnDownBlock2D", "AttnDownBlock2D", "AttnDownBlock2D")`): Tuple of downsample block
             types.

src/diffusers/models/unet_2d_condition.py

@@ -60,7 +60,7 @@ class UNet2DConditionModel(ModelMixin, ConfigMixin):
         in_channels (`int`, *optional*, defaults to 4): The number of channels in the input sample.
         out_channels (`int`, *optional*, defaults to 4): The number of channels in the output.
         center_input_sample (`bool`, *optional*, defaults to `False`): Whether to center the input sample.
-        flip_sin_to_cos (`bool`, *optional*, defaults to `False`):
+        flip_sin_to_cos (`bool`, *optional*, defaults to `True`):
             Whether to flip the sin to cos in the time embedding.
         freq_shift (`int`, *optional*, defaults to 0): The frequency shift to apply to the time embedding.
         down_block_types (`Tuple[str]`, *optional*, defaults to `("CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "DownBlock2D")`):