Fix typos in UNet2DConditionModel documentation (#7291)

* fix typo in UNet2DConditionModel documentation

* Fix indentation that may fix doc rendering

* Fix squished doc lines

Author: alexanderbonnet

src/diffusers/models/unets/unet_2d_condition.py

@@ -80,7 +80,7 @@ class UNet2DConditionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin,
         in_channels (`int`, *optional*, defaults to 4): Number of channels in the input sample.
         out_channels (`int`, *optional*, defaults to 4): 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")`):
@@ -109,7 +109,7 @@ class UNet2DConditionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin,
             The number of transformer blocks of type [`~models.attention.BasicTransformerBlock`]. Only relevant for
             [`~models.unet_2d_blocks.CrossAttnDownBlock2D`], [`~models.unet_2d_blocks.CrossAttnUpBlock2D`],
             [`~models.unet_2d_blocks.UNetMidBlock2DCrossAttn`].
-       reverse_transformer_layers_per_block : (`Tuple[Tuple]`, *optional*, defaults to None):
+        reverse_transformer_layers_per_block : (`Tuple[Tuple]`, *optional*, defaults to None):
             The number of transformer blocks of type [`~models.attention.BasicTransformerBlock`], in the upsampling
             blocks of the U-Net. Only relevant if `transformer_layers_per_block` is of type `Tuple[Tuple]` and for
             [`~models.unet_2d_blocks.CrossAttnDownBlock2D`], [`~models.unet_2d_blocks.CrossAttnUpBlock2D`],
@@ -147,9 +147,9 @@ class conditioning with `class_embed_type` equal to `None`.
             The second activation function to use in timestep embedding. Choose from `silu`, `mish` and `gelu`.
         time_cond_proj_dim (`int`, *optional*, defaults to `None`):
             The dimension of `cond_proj` layer in the timestep embedding.
-        conv_in_kernel (`int`, *optional*, default to `3`): The kernel size of `conv_in` layer. conv_out_kernel (`int`,
-        *optional*, default to `3`): The kernel size of `conv_out` layer. projection_class_embeddings_input_dim (`int`,
-        *optional*): The dimension of the `class_labels` input when
+        conv_in_kernel (`int`, *optional*, default to `3`): The kernel size of `conv_in` layer.
+        conv_out_kernel (`int`, *optional*, default to `3`): The kernel size of `conv_out` layer.
+        projection_class_embeddings_input_dim (`int`, *optional*): The dimension of the `class_labels` input when
             `class_embed_type="projection"`. Required when `class_embed_type="projection"`.
         class_embeddings_concat (`bool`, *optional*, defaults to `False`): Whether to concatenate the time
             embeddings with the class embeddings.