Functions — github.com/Vchitect/LaVie

CodeHub MCPcopy Create free account

hub / github.com/Vchitect/LaVie / functions

Functions553 in github.com/Vchitect/LaVie

⨍ Functions 553◇ Types & classes 134

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

base/models/unet_blocks.py:320

(self, hidden_states, temb=None)

base/models/unet_blocks.py:417

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

base/models/unet_blocks.py:524

(self, hidden_states, res_hidden_states_tuple, temb=None, upsample_size=None)

base/models/unet_blocks.py:625

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

base/models/attention.py:146

(self, hidden_states, encoder_hidden_states=None, timestep=None, use_image_num=None, return_dict: bool = True)

base/models/attention.py:358

(self, hidden_states, encoder_hidden_states=None, timestep=None, attention_mask=None, video_length=None, use_i

base/models/attention.py:511

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

base/models/attention.py:580

(self, n, device)

base/models/attention.py:701

base/models/resnet.py:14

(self, hidden_states, output_size=None)

base/models/resnet.py:44

(self, hidden_states)

base/models/resnet.py:102

(self, input_tensor, temb)

base/models/resnet.py:177

(self, hidden_states, condition_video=None, encoder_hidden_states=None, timesteps=None, temb=None, attention_m

vsr/models/temporal_module.py:61

(self, hidden_states, condition_video=None, encoder_hidden_states=None, timesteps=None, temb=None, attention_m

vsr/models/temporal_module.py:151

(self, hidden_states, encoder_hidden_states=None, timestep=None, return_dict: bool = True)

vsr/models/temporal_module.py:255

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

vsr/models/temporal_module.py:408

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

vsr/models/temporal_module.py:501

(self, hidden_states, offset_hidden_states)

vsr/models/temporal_module.py:588

(self, x, timestep)

vsr/models/temporal_module.py:677

(self, n, device)

vsr/models/unet.py:89

vsr/models/clip.py:51

(self, text_prompts, train, force_drop_ids=None)

vsr/models/clip.py:85

r""" Args: sample (`torch.FloatTensor`): Input sample. sample_posterior (`bool`, *optional*, defaults to `False`): Whether to sample from

vsr/models/autoencoder_kl.py:308

vsr/models/upscaling.py:63

vsr/models/upscaling.py:76

(self, x, noise_level=None)

vsr/models/upscaling.py:86

(ctx, run_function, length, *args)

vsr/models/utils.py:44

vsr/models/utils.py:138

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

vsr/models/unet_blocks.py:226

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

vsr/models/unet_blocks.py:320

(self, hidden_states, temb=None)

vsr/models/unet_blocks.py:408

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

vsr/models/unet_blocks.py:515

(self, hidden_states, res_hidden_states_tuple, temb=None, upsample_size=None)

vsr/models/unet_blocks.py:606

Args: hidden_states ( When discrete, `torch.LongTensor` of shape `(batch size, num latent pixels)`. When continou

vsr/models/diffusers_attention.py:180

(self, hidden_states)

vsr/models/diffusers_attention.py:330

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

vsr/models/diffusers_attention.py:481

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

vsr/models/diffusers_attention.py:594

(self, hidden_states)

vsr/models/diffusers_attention.py:773

(self, hidden_states)

vsr/models/diffusers_attention.py:794

(self, hidden_states)

vsr/models/diffusers_attention.py:820

vsr/models/diffusers_attention.py:836

(self, x, timestep)

vsr/models/diffusers_attention.py:853

Args: hidden_states ( When discrete, `torch.LongTensor` of shape `(batch size, num latent pixels)`. When continuo

vsr/models/diffusers_attention.py:936

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

vsr/models/attention.py:156

(self, hidden_states, encoder_hidden_states=None, timestep=None, return_dict: bool = True)

vsr/models/attention.py:386

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

vsr/models/attention.py:552

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

vsr/models/attention.py:597

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

vsr/models/attention.py:673

(self, n, device)

vsr/models/attention.py:820

vsr/models/resnet.py:24

(self, hidden_states, output_size=None)

vsr/models/resnet.py:54

(self, hidden_states)

vsr/models/resnet.py:112

(self, input_tensor, temb)

vsr/models/resnet.py:187

(self, input_tensor, temb=None)

vsr/models/resnet.py:286

interpolation/models/clip.py:47

(self, text_prompts, train, force_drop_ids=None)

interpolation/models/clip.py:82

(ctx, run_function, length, *args)

interpolation/models/utils.py:44

interpolation/models/utils.py:138

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

interpolation/models/unet_blocks.py:220

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

interpolation/models/unet_blocks.py:312

(self, hidden_states, temb=None)

interpolation/models/unet_blocks.py:400

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

interpolation/models/unet_blocks.py:505

(self, hidden_states, res_hidden_states_tuple, temb=None, upsample_size=None)

interpolation/models/unet_blocks.py:596

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

interpolation/models/attention.py:149

(self, hidden_states, encoder_hidden_states=None, timestep=None, return_dict: bool = True)

interpolation/models/attention.py:406

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

interpolation/models/attention.py:566

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

interpolation/models/attention.py:610

interpolation/models/resnet.py:14

(self, hidden_states, output_size=None)

interpolation/models/resnet.py:44

(self, hidden_states)

interpolation/models/resnet.py:102

(self, input_tensor, temb)

interpolation/models/resnet.py:177

Methodforward_with_cfg

Forward, but also batches the unconditional forward pass for classifier-free guidance.

base/models/unet.py:514

Methodforward_with_cfg

Forward, but also batches the unconditional forward pass for classifier-free guidance.

vsr/models/unet.py:592

Methodforward_with_cfg

Forward, but also batches the unconditional forward pass for classifier-free guidance.

interpolation/models/unet.py:453

Functionget_grad_norm

r""" Copy from torch.nn.utils.clip_grad_norm_ Clips gradient norm of an iterable of parameters. The norm is computed over all gradients

interpolation/utils.py:26

Functionget_lr_scheduler

(optimizer, name, **kwargs)

base/models/__init__.py:18

Functionget_lr_scheduler

(optimizer, name, **kwargs)

vsr/models/__init__.py:14

Functionget_lr_scheduler

(optimizer, name, **kwargs)

interpolation/models/__init__.py:18

Functionget_models

vsr/models/__init__.py:23

Functionget_named_beta_schedule

Get a pre-defined beta schedule for the given name. The beta schedule library consists of beta schedules which remain similar in the l

vsr/diffusion/gaussian_diffusion.py:91

Functionget_named_beta_schedule

Get a pre-defined beta schedule for the given name. The beta schedule library consists of beta schedules which remain similar in the l

interpolation/diffusion/gaussian_diffusion.py:98

Methodget_timesteps

(self, num_inference_steps, strength, device)

vsr/models/pipeline_stable_diffusion_upscale_video_3d.py:454

Methodget_velocity

( self, sample: torch.FloatTensor, noise: torch.FloatTensor, timesteps: torch.IntTensor )

vsr/diffusion/scheduling_ddim.py:441

vsr/diffusion/gaussian_diffusion.py:55

interpolation/diffusion/gaussian_diffusion.py:54

Create a linear module.

base/models/utils.py:154

Create a linear module.

vsr/models/utils.py:154

Create a linear module.

interpolation/models/utils.py:154

Functionmask_generation

(mask_type, shape, dtype, device)

interpolation/utils.py:298

Functionmean_flat

Take the mean over all non-batch dimensions.

base/models/utils.py:115

Functionmean_flat

Take the mean over all non-batch dimensions.

vsr/models/utils.py:115

Functionmean_flat

Take the mean over all non-batch dimensions.

interpolation/models/utils.py:115

Functionnoise_like

(shape, device, repeat=False)

base/models/utils.py:187

Functionnoise_like

(shape, device, repeat=False)

vsr/models/utils.py:187

Functionnoise_like

(shape, device, repeat=False)

interpolation/models/utils.py:187

Functionnormalization

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

base/models/utils.py:122

Functionnormalization

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

vsr/models/utils.py:122

Functionnormalization

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

interpolation/models/utils.py:122

Methodp_mean_variance

( self, model, *args, **kwargs )

vsr/diffusion/respace.py:89

← previous next →401–500 of 553, ranked by callers