Functions — github.com/MooreThreads/Moore-AnimateAnyone

Methodforward

The [`Transformer2DModel`] forward method. Args: hidden_states (`torch.LongTensor` of shape `(batch size, num latent pix

src/models/transformer_2d.py:213

Methodforward

r""" Args: sample (`torch.FloatTensor`): (batch, channel, height, width) noisy inputs tensor timestep (`torch.FloatTen

src/models/unet_3d.py:417

Methodforward

r""" The [`UNet2DConditionModel`] forward method. Args: sample (`torch.FloatTensor`): The noisy input ten

src/models/unet_2d_condition.py:872

Methodforward

( self, hidden_states: torch.FloatTensor, attention_mask: Optional[torch.FloatTensor]

src/models/attention.py:178

Methodforward

( self, hidden_states, encoder_hidden_states=None, timestep=None, atte

src/models/attention.py:382

Methodforward

(self, x: torch.FloatTensor)

src/models/unet_2d_blocks.py:219

Methodforward

( self, hidden_states: torch.FloatTensor, temb: Optional[torch.FloatTensor] = None )

src/models/unet_2d_blocks.py:344

Methodforward

( self, hidden_states: torch.FloatTensor, temb: Optional[torch.FloatTensor] = None,

src/models/unet_2d_blocks.py:452

Methodforward

( self, hidden_states: torch.FloatTensor, temb: Optional[torch.FloatTensor] = None,

src/models/unet_2d_blocks.py:606

Methodforward

( self, hidden_states: torch.FloatTensor, temb: Optional[torch.FloatTensor] = None,

src/models/unet_2d_blocks.py:737

Methodforward

( self, hidden_states: torch.FloatTensor, res_hidden_states_tuple: Tuple[torch.FloatTe

src/models/unet_2d_blocks.py:872

Methodforward

( self, hidden_states: torch.FloatTensor, res_hidden_states_tuple: Tuple[torch.FloatTe

src/models/unet_2d_blocks.py:1014

Methodforward

( self, hidden_states, temb=None, encoder_hidden_states=None, attentio

src/models/unet_3d_blocks.py:282

Methodforward

( self, hidden_states, temb=None, encoder_hidden_states=None, attentio

src/models/unet_3d_blocks.py:422

Methodforward

(self, hidden_states, temb=None, encoder_hidden_states=None)

src/models/unet_3d_blocks.py:570

Methodforward

( self, hidden_states, res_hidden_states_tuple, temb=None, encoder_hid

src/models/unet_3d_blocks.py:719

Methodforward

( self, hidden_states, res_hidden_states_tuple, temb=None, upsample_si

src/models/unet_3d_blocks.py:859

Methodforward

(self, conditioning)

src/models/pose_guider.py:47

Methodforward

(self, x)

src/models/resnet.py:10

Methodforward

(self, x)

src/models/resnet.py:21

Methodforward

(self, hidden_states, output_size=None)

src/models/resnet.py:53

Methodforward

(self, hidden_states)

src/models/resnet.py:112

Methodforward

(self, input_tensor, temb)

src/models/resnet.py:217

Methodforward

( self, input_tensor, temb, encoder_hidden_states, attention_mask=None

src/models/motion_module.py:77

Methodforward

(self, hidden_states, encoder_hidden_states=None, attention_mask=None)

src/models/motion_module.py:146

Methodforward

( self, hidden_states, encoder_hidden_states=None, attention_mask=None,

src/models/motion_module.py:236

Methodforward

(self, x)

src/models/motion_module.py:275

Methodforward

( self, hidden_states, encoder_hidden_states=None, attention_mask=None,

src/models/motion_module.py:351

Functionget_down_block

( down_block_type, num_layers, in_channels, out_channels, temb_channels, add_downsampl

src/models/unet_3d_blocks.py:15

Functionget_total_steps

( scheduler, timesteps: List[int], num_steps: Optional[int] = None, num_frames: int = ...,

src/pipelines/context.py:52

Functionget_up_block

( up_block_type, num_layers, in_channels, out_channels, prev_output_channel, temb_chan

src/models/unet_3d_blocks.py:98

Methodhacked_basic_transformer_inner_forward

( self, hidden_states: torch.FloatTensor, attention_mask: Optional[torch.F

src/models/mutual_self_attention.py:93

FunctionhandDetect

(candidate, subset, oriImg)

src/dwpose/util.py:230

Functionlinear

(v1, v2, t)

src/pipelines/utils.py:15

Functionnpmax

(array)

src/dwpose/util.py:373

FunctionpadRightDownCorner

(img, stride, padValue)

src/dwpose/util.py:47

Methodprepare_condition

( self, cond_image, width, height, device, dtype, do_c

src/pipelines/pipeline_pose2img.py:172

Functionprocess_batch_videos

(video_list, detector, root_dir, save_dir)

tools/extract_dwpose_from_vid.py:38

Functionread_image

(image)

app.py:215

Functionread_video

(video)

app.py:212

Methodset_attn_processor

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o

src/models/unet_3d.py:379

Methodset_chunk_feed_forward

(self, chunk_size: Optional[int], dim: int = 0)

src/models/attention.py:173

Methodset_default_attn_processor

Disables custom attention processors and sets the default attention implementation.

src/models/unet_2d_condition.py:741

Functionset_tensor_interpolation_method

(is_slerp)

src/pipelines/utils.py:10

Methodset_use_memory_efficient_attention_xformers

( self, use_memory_efficient_attention_xformers: bool, attention_op: Optional[Callable

src/models/motion_module.py:309

Functionslerp

( v0: torch.Tensor, v1: torch.Tensor, t: float, DOT_THRESHOLD: float = 0.9995 )

src/pipelines/utils.py:19

Functionsmart_resize

(x, s)

src/dwpose/util.py:11

Functionsmart_resize_k

(x, fx, fy)

src/dwpose/util.py:29

Functiontransfer

(model, model_weights)

src/dwpose/util.py:70

Functionuniform

( step: int = ..., num_steps: Optional[int] = None, num_frames: int = ..., context_size: Optio

src/pipelines/context.py:15

Functions250 in github.com/MooreThreads/Moore-AnimateAnyone