[Sync] diffusers commit 4a34307

diffusers commit 4a34307
    add: utility to format our docs too 📜 (huggingface/diffusers#7314)

models/attention_processor.py

@@ -1318,9 +1318,9 @@ def __call__(
 
 class FusedAttnProcessor2_0:
  r"""
- Processor for implementing scaled dot-product attention (enabled by default if you're using PyTorch 2.0).
- It uses fused projection layers. For self-attention modules, all projection matrices (i.e., query,
- key, value) are fused. For cross-attention modules, key and value projection matrices are fused.
+ Processor for implementing scaled dot-product attention (enabled by default if you're using PyTorch 2.0). It uses
+ fused projection layers. For self-attention modules, all projection matrices (i.e., query, key, value) are fused.
+ For cross-attention modules, key and value projection matrices are fused.
 
  <Tip warning={true}>
 

models/autoencoders/autoencoder_kl.py

@@ -311,8 +311,8 @@ def forward(
  # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.fuse_qkv_projections
  def fuse_qkv_projections(self):
  """
- Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query,
- key, value) are fused. For cross-attention modules, key and value projection matrices are fused.
+ Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value)
+ are fused. For cross-attention modules, key and value projection matrices are fused.
 
  <Tip warning={true}>
 

models/resnet.py

@@ -63,8 +63,8 @@ class ResnetBlock3D(nn.Module):
  eps (`float`, *optional*, defaults to `1e-6`): The epsilon to use for the normalization.
  non_linearity (`str`, *optional*, default to `"swish"`): the activation function to use.
  time_embedding_norm (`str`, *optional*, default to `"default"` ): Time scale shift config.
- By default, apply timestep embedding conditioning with a simple shift mechanism. Choose "scale_shift"
- for a stronger conditioning with scale and shift.
+ By default, apply timestep embedding conditioning with a simple shift mechanism. Choose "scale_shift" for a
+ stronger conditioning with scale and shift.
  kernel (`torch.FloatTensor`, optional, default to None)
  output_scale_factor (`float`, *optional*, default to be `1.0`): the scale factor to use for the output.
  use_in_shortcut (`bool`, *optional*, default to `True`):

models/unets/unet_3d_condition.py

@@ -883,8 +883,8 @@ def disable_freeu(self):
 
  def fuse_qkv_projections(self):
  """
- Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query,
- key, value) are fused. For cross-attention modules, key and value projection matrices are fused.
+ Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value)
+ are fused. For cross-attention modules, key and value projection matrices are fused.
 
  <Tip warning={true}>
 
@@ -1121,8 +1121,8 @@ def forward(
 
  Returns:
  [`~models.unets.unet_3d_condition.UNet3DConditionOutput`] or `tuple`:
- If `return_dict` is True, an [`~models.unets.unet_3d_condition.UNet3DConditionOutput`] is returned, otherwise
- a `tuple` is returned where the first element is the sample tensor.
+ If `return_dict` is True, an [`~models.unets.unet_3d_condition.UNet3DConditionOutput`] is returned,
+ otherwise a `tuple` is returned where the first element is the sample tensor.
  """
  # By default samples have to be AT least a multiple of the overall upsampling factor.
  # The overall upsampling factor is equal to 2 ** (# num of upsampling layers).