make style

Author: a-r-r-o-w

src/diffusers/models/transformers/latte_transformer_3d.py

@@ -12,15 +12,14 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from typing import Dict, Optional, Union
+from typing import Optional
 
 import torch
 from torch import nn
 
 from ...configuration_utils import ConfigMixin, register_to_config
 from ...models.embeddings import PixArtAlphaTextProjection, get_1d_sincos_pos_embed_from_grid
 from ..attention import BasicTransformerBlock
-from ..attention_processor import AttentionProcessor
 from ..embeddings import PatchEmbed
 from ..modeling_outputs import Transformer2DModelOutput
 from ..modeling_utils import ModelMixin

src/diffusers/pipelines/pyramid_attention_broadcast_utils.py

@@ -150,7 +150,6 @@ def apply_pyramid_attention_broadcast(
     >>> apply_pyramid_attention_broadcast(pipe, config)
     ```
     """
-    # We present Pyramid Attention Broadcast (PAB), a real-time, high quality and training-free approach for DiT-based video generation. Our method is founded on the observation that attention difference in the diffusion process exhibits a U-shaped pattern, indicating significant redundancy. We mitigate this by broadcasting attention outputs to subsequent steps in a pyramid style. It applies different broadcast strategies to each attention based on their variance for best efficiency. We further introduce broadcast sequence parallel for more efficient distributed inference. PAB demonstrates superior results across three models compared to baselines, achieving real-time generation for up to 720p videos. We anticipate that our simple yet effective method will serve as a robust baseline and facilitate future research and application for video generation.
     if config is None:
         config = PyramidAttentionBroadcastConfig()