Types & classes — github.com/Francis-Rings/MotionFollower

CodeHub MCPcopy Create free account

hub / github.com/Francis-Rings/MotionFollower / types & classes

Types & classes56 in github.com/Francis-Rings/MotionFollower

⨍ Functions 192◇ Types & classes 56

↓ 13 callersClassInflatedConv3d

src/models/resnet.py:7

↓ 6 callersClassResnetBlock3D

src/models/resnet.py:116

↓ 4 callersClassAttnProcessor

r""" Default processor for performing attention-related computations.

src/models/attn_process_diffuser.py:702

↓ 4 callersClassAttnProcessor2_0

r""" Processor for implementing scaled dot-product attention (enabled by default if you're using PyTorch 2.0).

src/models/attn_process_diffuser.py:1174

↓ 4 callersClassInflatedGroupNorm

src/models/resnet.py:18

↓ 3 callersClassAttention

r""" A cross attention layer. Parameters: query_dim (`int`): The number of channels in the query. cross_att

src/models/attn_process_diffuser.py:25

↓ 3 callersClassAttnProcessor

src/models/attention_processor.py:11

↓ 3 callersClassTransformer3DModel

src/models/transformer_3d.py:46

↓ 2 callersClassAppearance_Adapter

src/models/appearance_net.py:32

↓ 2 callersClassAttnAddedKVProcessor

r""" Processor for performing attention-related computations with extra learnable key and value matrices for the text encoder.

src/models/attn_process_diffuser.py:875

↓ 2 callersClassDownsample3D

src/models/resnet.py:86

↓ 2 callersClassResnetBlock

src/models/appearance_net.py:65

↓ 2 callersClassUNetMidBlock3DCrossAttn

src/models/unet_3d_blocks.py:177

↓ 2 callersClassUpsample3D

src/models/resnet.py:29

↓ 2 callersClassXFormersAttnProcessor

r""" Processor for implementing memory efficient attention using xFormers. Args: attention_op (`Callable`, *optional*, defaults t

src/models/attn_process_diffuser.py:1083

↓ 1 callersClassCrossAttnDownBlock3D

src/models/unet_3d_blocks.py:313

↓ 1 callersClassCrossAttnUpBlock3D

src/models/unet_3d_blocks.py:637

↓ 1 callersClassCustomDiffusionXFormersAttnProcessor

r""" Processor for implementing memory efficient attention using xFormers for the Custom Diffusion method. Args: train_kv (`bool`, de

src/models/attn_process_diffuser.py:1262

↓ 1 callersClassDownBlock3D

src/models/unet_3d_blocks.py:509

↓ 1 callersClassDownsample

src/models/appearance_net.py:101

↓ 1 callersClassEstimatorOutput

src/models/estimator.py:25

↓ 1 callersClassLoRAXFormersAttnProcessor

r""" Processor for implementing the LoRA attention mechanism with memory efficient attention using xFormers. Args: hidden_size (`

src/models/attn_process_diffuser.py:1848

↓ 1 callersClassMish

src/models/resnet.py:243

↓ 1 callersClassMotionEditor

src/pipelines/motion_editor.py:33

↓ 1 callersClassMotionEditorOutput

src/pipelines/motion_editor.py:29

↓ 1 callersClassPose2VideoCollectionPipeline

src/pipelines/pipeline_pose2vid_collection.py:27

↓ 1 callersClassPose2VideoCollectionPipelineOutput

src/pipelines/pipeline_pose2vid_collection.py:21

↓ 1 callersClassPoseGuider

src/models/pose_guider.py:12

↓ 1 callersClassPositionalEncoding

src/models/motion_module.py:261

↓ 1 callersClassSlicedAttnAddedKVProcessor

r""" Processor for implementing sliced attention with extra learnable key and value matrices for the text encoder. Args: slice_si

src/models/attn_process_diffuser.py:1579

↓ 1 callersClassSlicedAttnProcessor

r""" Processor for implementing sliced attention. Args: slice_size (`int`, *optional*): The number of steps to compu

src/models/attn_process_diffuser.py:1492

↓ 1 callersClassSpatialNorm

Spatially conditioned normalization as defined in https://arxiv.org/abs/2209.09002. Args: f_channels (`int`): The n

src/models/attn_process_diffuser.py:1671

↓ 1 callersClassTemporalBasicTransformerBlock

src/models/attention.py:21

↓ 1 callersClassTemporalTransformer3DModel

src/models/motion_module.py:93

↓ 1 callersClassTemporalTransformerBlock

src/models/motion_module.py:184

↓ 1 callersClassTransformer3DModelOutput

src/models/transformer_3d.py:15

↓ 1 callersClassUNet3DConditionOutput

src/models/unet_3d.py:24

↓ 1 callersClassUpBlock3D

src/models/unet_3d_blocks.py:815

↓ 1 callersClassVanillaTemporalModule

src/models/motion_module.py:43

↓ 1 callersClassVersatileAttention

src/models/motion_module.py:279

↓ 1 callersClassXFormersAttnAddedKVProcessor

r""" Processor for implementing memory efficient attention using xFormers. Args: attention_op (`Callable`, *optional*, defaults t

src/models/attn_process_diffuser.py:1012

ClassAttnAddedKVProcessor2_0

r""" Processor for performing scaled dot-product attention (enabled by default if you're using PyTorch 2.0), with extra learnable key and va

src/models/attn_process_diffuser.py:939

ClassCustomDiffusionAttnProcessor

r""" Processor for implementing attention for the Custom Diffusion method. Args: train_kv (`bool`, defaults to `True`):

src/models/attn_process_diffuser.py:771

ClassCustomDiffusionAttnProcessor2_0

r""" Processor for implementing attention for the Custom Diffusion method using PyTorch 2.0’s memory-efficient scaled dot-product attention.

src/models/attn_process_diffuser.py:1378

ClassDDIMInversion

src/utils/inversion.py:7

src/models/estimator.py:28

ClassFinalLayer

src/models/transformer_3d.py:30

ClassIPAdapterAttnProcessor

r""" Attention processor for IP-Adapater. Args: hidden_size (`int`): The hidden size of the attention layer.

src/models/attn_process_diffuser.py:1986

ClassIPAdapterAttnProcessor2_0

r""" Attention processor for IP-Adapater for PyTorch 2.0. Args: hidden_size (`int`): The hidden size of the attentio

src/models/attn_process_diffuser.py:2096

ClassKandi3AttnProcessor

r""" Default kandinsky3 proccesor for performing attention-related computations.

src/models/attn_process_diffuser.py:2232

ClassLoRAAttnAddedKVProcessor

r""" Processor for implementing the LoRA attention mechanism with extra learnable key and value matrices for the text encoder. Args:

src/models/attn_process_diffuser.py:1927

ClassLoRAAttnProcessor

r""" Processor for implementing the LoRA attention mechanism. Args: hidden_size (`int`, *optional*): The hidden size

src/models/attn_process_diffuser.py:1701

ClassLoRAAttnProcessor2_0

r""" Processor for implementing the LoRA attention mechanism using PyTorch 2.0's memory-efficient scaled dot-product attention. Args:

src/models/attn_process_diffuser.py:1773

ClassMyNullInversion

src/pipelines/null_text_optimization.py:28

ClassTemporalTransformer3DModelOutput

src/models/motion_module.py:22

ClassUNet3DConditionModel

src/models/unet_3d.py:27