MCPcopy Create free account

hub / github.com/Francis-Rings/StableAnimator / functions

Functions480 in github.com/Francis-Rings/StableAnimator

⨍ Functions 480◇ Types & classes 92
↓ 1 callersMethodprepare_latents
( self, batch_size: int, num_frames: int, num_channels_lat
animation/pipelines/inference_pipeline_animation.py:294
↓ 1 callersMethodprepare_latents
( self, batch_size: int, num_frames: int, num_channels_latents: int, h
animation/pipelines/pipeline_animation.py:315
↓ 1 callersMethodprepare_latents
( self, batch_size: int, num_frames: int, num_channels_lat
animation/pipelines/validation_pipeline_animation.py:322
↓ 1 callersMethodprepare_latents
( self, batch_size: int, num_frames: int, num_channels_lat
animation/pipelines/inference_pipeline_animation_pro.py:297
↓ 1 callersFunctionpreprocess
(img, input_size, swap=(2, 0, 1))
DWPose/dwpose_utils/onnxdet.py:80
↓ 1 callersFunctionpreprocess
Do preprocessing for RTMPose model inference. Args: img (np.ndarray): Input image in shape. input_size (tuple): Input image size
DWPose/dwpose_utils/onnxpose.py:7
↓ 1 callersFunctionrand_cosine_interpolated
Draws samples from an interpolated cosine timestep distribution (from simple diffusion).
train.py:184
↓ 1 callersFunctionrand_cosine_interpolated
Draws samples from an interpolated cosine timestep distribution (from simple diffusion).
train_single.py:185
↓ 1 callersMethodrandom_masking
Perform per-sample random masking by per-sample shuffling. Per-sample shuffling is done by argsort random noise. x: [N, L, D]
animation/helper/backbones/vit.py:224
↓ 1 callersFunctionread_template_media_list
(path)
animation/helper/eval_ijbc.py:120
↓ 1 callersFunctionread_template_media_list
(path)
animation/helper/onnx_ijbc.py:79
↓ 1 callersFunctionread_template_pair_list
(path)
animation/helper/eval_ijbc.py:131
↓ 1 callersFunctionread_template_pair_list
(path)
animation/helper/onnx_ijbc.py:86
↓ 1 callersFunctionread_template_pair_list
(path)
animation/helper/utils/plot.py:18
↓ 1 callersFunctionrescale_zero_terminal_snr
Rescales betas to have zero terminal SNR Based on https://arxiv.org/pdf/2305.08891.pdf (Algorithm 1) Args: betas (`torch.Tenso
animation/pipelines/euler_discrete_pro.py:183
↓ 1 callersMethodreset
(self)
animation/helper/dataset.py:282
↓ 1 callersFunctionsave_frames_as_mp4
(frames, output_mp4_path, fps)
app.py:54
↓ 1 callersFunctionsave_frames_as_png
(frames, output_path)
inference_basic.py:39
↓ 1 callersFunctionsave_frames_as_png
(frames, output_path)
app.py:45
↓ 1 callersFunctionseed_everything
(seed)
inference_op.py:25
↓ 1 callersFunctionseed_everything
(seed)
inference_basic.py:20
↓ 1 callersMethodset_attn_processor
r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor`
animation/modules/refined_vae.py:258
↓ 1 callersMethodset_ip_adapter
(self)
animation/pipelines/pipeline_animation.py:144
↓ 1 callersFunctionsetup_seed
(seed, cuda_deterministic=True)
animation/helper/utils/utils_distributed_sampler.py:11
↓ 1 callersFunctionstratified_uniform
Draws stratified samples from a uniform distribution.
train.py:172
↓ 1 callersFunctionstratified_uniform
Draws stratified samples from a uniform distribution.
train_single.py:173
↓ 1 callersFunctionsync_random_seed
Make sure different ranks share the same seed. All workers must call this function, otherwise it will deadlock. This method is generally used
animation/helper/utils/utils_distributed_sampler.py:45
↓ 1 callersFunctiontensor2vid
(video, processor, output_type="np")
animation/utils/utils.py:47
↓ 1 callersFunctiontensor2vid
(video: torch.Tensor, processor: "VaeImageProcessor", output_type: str = "np")
animation/pipelines/inference_pipeline_animation.py:31
↓ 1 callersFunctiontensor2vid
(video: torch.Tensor, processor: "VaeImageProcessor", output_type: str = "np")
animation/pipelines/pipeline_animation.py:38
↓ 1 callersFunctiontensor2vid
(video: torch.Tensor, processor: "VaeImageProcessor", output_type: str = "np")
animation/pipelines/validation_pipeline_animation.py:59
↓ 1 callersFunctiontensor2vid
(video: torch.Tensor, processor: "VaeImageProcessor", output_type: str = "np")
animation/pipelines/inference_pipeline_animation_pro.py:59
↓ 1 callersFunctiontensor2vid_scheduler_new
(video, processor, output_type="np")
animation/pipelines/euler_discrete_pro.py:85
↓ 1 callersFunctiontop_down_affine
Get the bbox image as the model input by affine transform. Args: input_size (dict): The input size of the model. bbox_scale (dict
DWPose/dwpose_utils/onnxpose.py:255
↓ 1 callersFunctionvalidate_and_convert_image
(image, target_size=(256, 256))
train.py:56
↓ 1 callersFunctionvalidate_and_convert_image
(image, target_size=(256, 256))
train_single.py:57
↓ 1 callersMethodver_test
(self, backbone: torch.nn.Module, global_step: int)
animation/helper/utils/utils_callbacks.py:28
↓ 1 callersFunctionverification
(template_norm_feats=None, unique_templates=None, p1=None,
animation/helper/eval_ijbc.py:252
↓ 1 callersFunctionverification
(template_norm_feats=None, unique_templates=None, p1=None,
animation/helper/onnx_ijbc.py:126
Method__call__
( self, attn, hidden_states, encoder_hidden_states=None, attentio
animation/modules/attention_processor.py:34
Method__call__
( self, attn, hidden_states, encoder_hidden_states=None, attentio
animation/modules/attention_processor.py:144
Method__call__
( self, attn, hidden_states, encoder_hidden_states=None,
animation/modules/attention_processor_normalized.py:36
Method__call__
r""" The call function to the pipeline for generation. Args: image (`PIL.Image.Image` or `List[PIL.Image.Image]` or `
animation/pipelines/inference_pipeline_animation.py:363
Method__call__
r""" The call function to the pipeline for generation. Args: image (`PIL.Image.Image` or `List[PIL.Image.Image]` or `torc
animation/pipelines/pipeline_animation.py:384
Method__call__
r""" The call function to the pipeline for generation. Args: image (`PIL.Image.Image` or `List[PIL.Image.Image]` or `
animation/pipelines/validation_pipeline_animation.py:391
Method__call__
r""" The call function to the pipeline for generation. Args: image (`PIL.Image.Image` or `List[PIL.Image.Image]` or `
animation/pipelines/inference_pipeline_animation_pro.py:366
Method__call__
(self, num_update, backbone: torch.nn.Module)
animation/helper/utils/utils_callbacks.py:61
Method__call__
(self, global_step: int, loss: AverageMeter, epoch: int,
animation/helper/utils/utils_callbacks.py:82
Method__call__
(self, oriImg)
DWPose/dwpose_utils/wholebody.py:20
Method__call__
(self, oriImg, remain_face=True)
DWPose/dwpose_utils/__init__.py:38
Method__call__
(self, oriImg, remain_face=True)
DWPose/dwpose_utils/__init__.py:80
Method__call__
(self, oriImg)
DWPose/dwpose_utils/dwpose_detector.py:20
Method__getitem__
(self, idx)
animation/dataset/animation_dataset.py:85
Method__getitem__
(self, idx)
animation/helper/onnx_ijbc.py:39
Method__getitem__
(self, index)
animation/helper/dataset.py:159
Method__getitem__
(self, index)
animation/helper/dataset.py:186
Method__init__
(self, **kwargs)
train.py:835
Method__init__
(self, **kwargs)
train_single.py:846
Method__init__
( self, hidden_size, cross_attention_dim=None, rank=4,
animation/modules/attention_processor.py:118
Method__init__
( self, sample_size: Optional[int] = None, in_channels: int = 8,
animation/modules/unet.py:74
Method__init__
(self)
animation/modules/face_model.py:9
Method__init__
( self, num_attention_heads: int = 16, attention_head_dim: int = 88, in_ch
animation/modules/transformer_temporal.py:218
Method__init__
( self, hidden_size, cross_attention_dim=None, rank=4,
animation/modules/attention_processor_normalized.py:15
Method__init__
( self, num_attention_heads: int = 16, attention_head_dim: int = 88,
animation/modules/attention.py:203
Method__init__
(self, noise_latent_channels=320)
animation/modules/pose_net.py:11
Method__init__
(self, *args, **kwargs)
animation/modules/unet_3d_blocks.py:51
Method__init__
(self, *args, **kwargs)
animation/modules/unet_3d_blocks.py:58
Method__init__
(self, *args, **kwargs)
animation/modules/unet_3d_blocks.py:65
Method__init__
(self, *args, **kwargs)
animation/modules/unet_3d_blocks.py:72
Method__init__
(self, *args, **kwargs)
animation/modules/unet_3d_blocks.py:79
Method__init__
( self, in_channels: int, temb_channels: int, dropout: float = 0.0,
animation/modules/unet_3d_blocks.py:278
Method__init__
( self, in_channels: int, out_channels: int, temb_channels: int,
animation/modules/unet_3d_blocks.py:412
Method__init__
( self, in_channels: int, out_channels: int, temb_channels: int,
animation/modules/unet_3d_blocks.py:554
Method__init__
( self, in_channels: int, out_channels: int, prev_output_channel: int,
animation/modules/unet_3d_blocks.py:643
Method__init__
( self, in_channels: int, out_channels: int, attention_head_dim: int = 512
animation/modules/unet_3d_blocks.py:903
Method__init__
( self, in_channels: int, out_channels: int, num_layers: int = 1,
animation/modules/unet_3d_blocks.py:966
Method__init__
( self, in_channels: int, temb_channels: int, num_layers: int = 1,
animation/modules/unet_3d_blocks.py:1016
Method__init__
( self, in_channels: int, out_channels: int, temb_channels: int,
animation/modules/unet_3d_blocks.py:1126
Method__init__
( self, in_channels: int, out_channels: int, temb_channels: int,
animation/modules/unet_3d_blocks.py:1216
Method__init__
( self, in_channels: int, prev_output_channel: int, out_channels: int,
animation/modules/unet_3d_blocks.py:1338
Method__init__
( self, in_channels: int, out_channels: int, prev_output_channel: int,
animation/modules/unet_3d_blocks.py:1427
Method__init__
( self, in_channels: int = 3, out_channels: int = 3, down_block_types: Tup
animation/modules/refined_vae.py:186
Method__init__
(self, *, dim, dim_head=64, heads=8)
animation/modules/id_encoder.py:14
Method__init__
( self, dim=768, depth=4, dim_head=64, heads=16, embeddi
animation/modules/id_encoder.py:70
Method__init__
construnct base model components and load pretrained svd model except pose-net Args: base_model_path (str): pretrained svd model p
animation/utils/loader.py:16
Method__init__
(self, root_path, txt_path, width, height, n_sample_frames, sample_frame_rate, sample_margin=30,
animation/dataset/animation_dataset.py:15
Method__init__
( self, vae, image_encoder, unet, scheduler,
animation/pipelines/inference_pipeline_animation.py:82
Method__init__
( self, vae, image_encoder, unet, scheduler: EulerDiscreteScheduler,
animation/pipelines/pipeline_animation.py:99
Method__init__
( self, vae, image_encoder, unet, scheduler,
animation/pipelines/validation_pipeline_animation.py:110
Method__init__
( self, num_train_timesteps: int = 1000, beta_start: float = 0.0001, beta_
animation/pipelines/euler_discrete_pro.py:266
Method__init__
( self, vae, image_encoder, unet, scheduler,
animation/pipelines/inference_pipeline_animation_pro.py:110
Method__init__
(self, prefix, data_shape, batch_size=1)
animation/helper/eval_ijbc.py:55
Method__init__
(self, root, lines, align=True)
animation/helper/onnx_ijbc.py:31
Method__init__
(self, model_path, cpu=False)
animation/helper/onnx_helper.py:16
Method__init__
(self, generator, local_rank, max_prefetch=6)
animation/helper/dataset.py:80
Method__init__
(self, local_rank, **kwargs)
animation/helper/dataset.py:109
Method__init__
(self, root_dir, local_rank)
animation/helper/dataset.py:138
Method__init__
(self)
animation/helper/dataset.py:177
Method__init__
(self)
animation/helper/partial_fc_v2.py:223
Method__init__
(self, s, m1, m2, m3, i
animation/helper/losses.py:6
← previousnext →201–300 of 480, ranked by callers