MCPcopy Create free account

hub / github.com/TencentARC/AnimeGamer / functions

Functions1,003 in github.com/TencentARC/AnimeGamer

⨍ Functions 1,003◇ Types & classes 263↳ Endpoints 4
↓ 1 callersMethod_forward
(self, x, context=None, timesteps=None)
VDM_Decoder/sgm/modules/video_attention.py:105
↓ 1 callersFunction_get_unpad_data
(attention_mask)
MLLM/src/models/mistral/modeling_mistral.py:68
↓ 1 callersMethod_init_embedder
(self, config, freeze=True)
VDM_Decoder/diffusion_video.py:141
↓ 1 callersMethod_init_first_stage
(self, config)
VDM_Decoder/diffusion_video.py:154
↓ 1 callersMethod_init_lora
(self, rank, scale, ckpt_dir=None)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:934
↓ 1 callersMethod_make_attn
(self)
VDM_Decoder/sgm/modules/diffusionmodules/model.py:638
↓ 1 callersMethod_make_conv
(self)
VDM_Decoder/sgm/modules/diffusionmodules/model.py:644
↓ 1 callersMethod_make_resblock
(self)
VDM_Decoder/sgm/modules/diffusionmodules/model.py:641
↓ 1 callersFunction_pass_from_previous_rank
(input_, dim, kernel_size)
VDM_Decoder/vae_modules/cp_enc_dec.py:197
↓ 1 callersFunction_prepare_4d_attention_sdpa
Prepares the correct `attn_mask` argument to be used by `torch.nn.functional.scaled_dot_product_attention`.
MLLM/src/models/mistral/modeling_attn_mask_utils.py:244
↓ 1 callersFunction_prepare_4d_causal_attention_mask
( attention_mask: Optional[torch.Tensor], input_shape: Union[torch.Size, Tuple, List], inputs_embe
MLLM/src/models/mistral/modeling_attn_mask_utils.py:220
↓ 1 callersMethod_scale_and_shift
(self, zhat_normalized: Tensor)
VDM_Decoder/sgm/modules/autoencoding/regularizers/finite_scalar_quantization.py:104
↓ 1 callersMethod_scale_and_shift_inverse
(self, zhat: Tensor)
VDM_Decoder/sgm/modules/autoencoding/regularizers/finite_scalar_quantization.py:108
↓ 1 callersMethod_unmask_unattended
( expanded_mask: torch.Tensor, attention_mask: torch.Tensor, unmasked_value: Union[bool, float] )
MLLM/src/models/mistral/modeling_attn_mask_utils.py:175
↓ 1 callersMethod_upad_input
(self, query_layer, key_layer, value_layer, attention_mask, query_length)
MLLM/src/models/mistral/modeling_mistral.py:557
↓ 1 callersMethodadd_model_specific_args
(cls, parser)
VDM_Decoder/sgm/models/sat_ours/base_model.py:174
↓ 1 callersFunctionadd_sampling_config_args
Sampling configurations
VDM_Decoder/arguments.py:31
↓ 1 callersFunctionappend_zero
(x)
VDM_Decoder/sgm/util.py:274
↓ 1 callersMethodattention
(self, h_: torch.Tensor)
VDM_Decoder/sgm/modules/diffusionmodules/model.py:194
↓ 1 callersFunctionattention_fn_default
(query_layer, key_layer, value_layer, attention_mask, attention_dropout=None, log_atten
VDM_Decoder/sgm/models/sat_ours/transformer_defaults.py:80
↓ 1 callersFunctionavg_pool_nd
Create a 1D, 2D, or 3D average pooling module.
VDM_Decoder/sgm/modules/diffusionmodules/util.py:215
↓ 1 callersMethodbound
Bound `z`, an array of shape (..., d).
VDM_Decoder/sgm/modules/autoencoding/regularizers/finite_scalar_quantization.py:91
↓ 1 callersFunctionbroadcat
(tensors, dim=-1)
VDM_Decoder/dit_video_concat.py:292
↓ 1 callersMethodcalculate_adaptive_weight
( self, nll_loss: torch.Tensor, g_loss: torch.Tensor, last_layer: torch.Tensor )
VDM_Decoder/sgm/modules/autoencoding/losses/discriminator_loss.py:188
↓ 1 callersFunctioncast_tuple
(t, length=1)
VDM_Decoder/sgm/modules/autoencoding/vqvae/movq_enc_3d.py:13
↓ 1 callersFunctioncast_tuple
(t, length=1)
VDM_Decoder/vae_modules/cp_enc_dec.py:26
↓ 1 callersMethodcluster_size_ema_update
(self, new_cluster_size)
VDM_Decoder/sgm/modules/autoencoding/regularizers/quantize.py:311
↓ 1 callersMethodcodes_to_indices
Converts a `code` to an index in the codebook.
VDM_Decoder/sgm/modules/autoencoding/regularizers/finite_scalar_quantization.py:112
↓ 1 callersFunctionconv_gather_from_context_parallel_region
(input_, dim, kernel_size)
VDM_Decoder/vae_modules/cp_enc_dec.py:348
↓ 1 callersFunctionconv_scatter_to_context_parallel_region
(input_, dim, kernel_size)
VDM_Decoder/vae_modules/cp_enc_dec.py:344
↓ 1 callersMethodcopy_to
(self, model)
VDM_Decoder/sgm/modules/ema.py:52
↓ 1 callersFunctioncosine_loss
(rec, target)
MLLM/src/models_clm/models.py:20
↓ 1 callersFunctioncount_params
(model, verbose=False)
VDM_Decoder/sgm/util.py:247
↓ 1 callersFunctioncuculate_level
(tire)
app.py:65
↓ 1 callersFunctioncuculate_level
(tire)
inference_Decoder.py:27
↓ 1 callersMethoddecode
( self, z: torch.Tensor, input_cp: bool = False, output_cp: bool = False,
VDM_Decoder/vae_modules/autoencoder.py:617
↓ 1 callersFunctiondivisible_by
(num, den)
VDM_Decoder/sgm/modules/autoencoding/vqvae/movq_dec_3d.py:14
↓ 1 callersFunctiondivisible_by
(num, den)
VDM_Decoder/sgm/modules/autoencoding/vqvae/movq_enc_3d.py:17
↓ 1 callersFunctiondivisible_by
(num, den)
VDM_Decoder/vae_modules/cp_enc_dec.py:30
↓ 1 callersFunctiondownload
(url, local_path, chunk_size=1024)
VDM_Decoder/sgm/modules/autoencoding/lpips/util.py:16
↓ 1 callersMethodembed_avg_ema_update
(self, new_embed_avg)
VDM_Decoder/sgm/modules/autoencoding/regularizers/quantize.py:314
↓ 1 callersMethodencode
(self, video: Tensor, quantize=False, cond: Optional[Tensor] = None, video_contains_first_frame=True)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:1383
↓ 1 callersMethodencode
(self, text)
VDM_Decoder/sgm/modules/encoders/modules.py:295
↓ 1 callersMethodencode
( self, x: torch.Tensor, return_reg_log: bool = False, unregularized: bool = F
VDM_Decoder/vae_modules/autoencoder.py:588
↓ 1 callersMethodencode_with_vision_transformer
(self, x)
VDM_Decoder/sgm/modules/encoders/ip_encoder.py:97
↓ 1 callersFunctionexists
(x)
VDM_Decoder/sgm/util.py:223
↓ 1 callersFunctionexists
(v)
VDM_Decoder/sgm/modules/autoencoding/regularizers/finite_scalar_quantization.py:19
↓ 1 callersFunctionexists
(x)
VDM_Decoder/vae_modules/utils.py:217
↓ 1 callersFunctionfake_cp_pass_from_previous_rank
(input_, dim, kernel_size, cache_padding)
VDM_Decoder/vae_modules/cp_enc_dec.py:356
↓ 1 callersMethodforward
(self, x)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:136
↓ 1 callersMethodforward
(self, x)
VDM_Decoder/sgm/modules/diffusionmodules/util.py:186
↓ 1 callersMethodforward
(self, x, t=None, context=None)
VDM_Decoder/sgm/modules/diffusionmodules/model.py:381
↓ 1 callersMethodforward
( self, video_or_images: Tensor, cond: Optional[Tensor] = None, return_loss=Fa
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:1509
↓ 1 callersMethodforward
(self, embed_id)
VDM_Decoder/sgm/modules/autoencoding/regularizers/quantize.py:308
↓ 1 callersMethodforward
(self, x)
VDM_Decoder/vae_modules/cp_enc_dec.py:544
↓ 1 callersMethodforward
(self, x)
MLLM/src/models/mistral/modeling_mistral.py:185
↓ 1 callersMethodfreeze
(self)
VDM_Decoder/sgm/modules/encoders/ip_encoder.py:87
↓ 1 callersMethodfreeze
(self)
VDM_Decoder/sgm/modules/encoders/modules.py:259
↓ 1 callersFunctiongenerate_Decoder
(ml, vid_output, video_path)
app.py:337
↓ 1 callersFunctiongenerate_MLLM
(history, characters, motion_adverb, motion, time, background)
app.py:178
↓ 1 callersFunctiongenerate_animation
(history, characters, motion_adverb, motion, time, background, video_dir)
app.py:391
↓ 1 callersFunctiongenerate_history_html
(history)
app.py:459
↓ 1 callersFunctionget_3d_sincos_pos_embed
grid_size: int of the grid height and width t_size: int of the temporal size return: pos_embed: [t_size*grid_size*grid_size, embed_di
VDM_Decoder/dit_video_concat.py:130
↓ 1 callersMethodget_alpha
(self, image_only_indicator: torch.Tensor)
VDM_Decoder/sgm/modules/diffusionmodules/util.py:250
↓ 1 callersMethodget_alpha
(self, bs)
VDM_Decoder/sgm/modules/autoencoding/temporal_ae.py:54
↓ 1 callersMethodget_alpha
( self, )
VDM_Decoder/sgm/modules/autoencoding/temporal_ae.py:163
↓ 1 callersMethodget_alpha
( self, )
VDM_Decoder/sgm/modules/autoencoding/temporal_ae.py:229
↓ 1 callersMethodget_args
Get the parsed args of the current model. Args: **kwargs: will override the default args. Returns:
VDM_Decoder/sgm/models/sat_ours/base_model.py:278
↓ 1 callersFunctionget_color_class
(value)
app.py:451
↓ 1 callersMethodget_discriminator_params
(self)
VDM_Decoder/vae_modules/autoencoder.py:208
↓ 1 callersMethodget_loss
(self, model_output, target, w)
VDM_Decoder/sgm/modules/diffusionmodules/loss.py:57
↓ 1 callersMethodget_loss
(self, model_output, target, w)
VDM_Decoder/sgm/modules/diffusionmodules/loss.py:147
↓ 1 callersMethodget_mult
(self, h, s, t, t_next)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:267
↓ 1 callersMethodget_mult
(self, h, r, t, t_next, previous_sigma)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:310
↓ 1 callersMethodget_mult
(self, h, r, t, t_next, previous_sigma)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:381
↓ 1 callersMethodget_mult
(self, h, r, alpha_cumprod_sqrt, next_alpha_cumprod_sqrt, previous_alpha_cumprod_sqrt)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:590
↓ 1 callersMethodget_mult
(self, h, r, alpha_cumprod_sqrt, next_alpha_cumprod_sqrt, previous_alpha_cumprod_sqrt)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:707
↓ 1 callersMethodget_nll_loss
( self, rec_loss: torch.Tensor, weights: Optional[Union[float, torch.Tensor]] = None,
VDM_Decoder/sgm/modules/autoencoding/losses/discriminator_loss.py:289
↓ 1 callersFunctionget_timestep_embedding
This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches
VDM_Decoder/sgm/modules/diffusionmodules/model.py:23
↓ 1 callersMethodget_trainable_autoencoder_parameters
(self)
VDM_Decoder/sgm/modules/autoencoding/losses/discriminator_loss.py:84
↓ 1 callersMethodget_trainable_params
(self)
VDM_Decoder/sgm/modules/autoencoding/losses/video_loss.py:549
↓ 1 callersMethodget_variables
(self, sigma, sigma_down)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:261
↓ 1 callersMethodget_variables
(self, sigma, next_sigma, previous_sigma=None)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:299
↓ 1 callersMethodget_variables
(self, sigma, next_sigma, previous_sigma=None)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:370
↓ 1 callersMethodget_variables
(self, alpha_cumprod_sqrt, next_alpha_cumprod_sqrt, previous_alpha_cumprod_sqrt=None)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:574
↓ 1 callersMethodget_variables
(self, alpha_cumprod_sqrt, next_alpha_cumprod_sqrt, previous_alpha_cumprod_sqrt=None)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:691
↓ 1 callersFunctiongmm_predict
(means, weights)
MLLM/src/models_clm/models.py:72
↓ 1 callersFunctiongmm_sample
(means, variances, weights)
MLLM/src/models_clm/models.py:93
↓ 1 callersFunctiongmm_sample_weighted
(means, variances, weights)
MLLM/src/models_clm/models.py:78
↓ 1 callersFunctiongmm_split_params
(gmm_params, k, d, var_scale=1.0)
MLLM/src/models_clm/models.py:51
↓ 1 callersFunctiongradient_penalty
(images, output)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:119
↓ 1 callersFunctiongradient_penalty
(images, output)
VDM_Decoder/sgm/modules/autoencoding/losses/video_loss.py:61
↓ 1 callersFunctionhinge_discr_loss
(fake, real)
VDM_Decoder/sgm/modules/autoencoding/losses/video_loss.py:37
↓ 1 callersFunctionhinge_gen_loss
(fake)
VDM_Decoder/sgm/modules/autoencoding/losses/video_loss.py:41
↓ 1 callersMethodidx_to_sigma
(self, idx)
VDM_Decoder/sgm/modules/diffusionmodules/sigma_sampling.py:71
↓ 1 callersMethodidx_to_sigma
(self, idx)
VDM_Decoder/sgm/modules/diffusionmodules/denoiser.py:62
↓ 1 callersMethodindices_to_codes
(self, indices, project_out=True)
VDM_Decoder/sgm/modules/autoencoding/regularizers/lookup_free_quantization.py:145
↓ 1 callersMethodindices_to_codes
Inverse of `codes_to_indices`.
VDM_Decoder/sgm/modules/autoencoding/regularizers/finite_scalar_quantization.py:118
↓ 1 callersMethodinit_conv_
(self, conv)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:749
↓ 1 callersMethodinit_conv_
(self, conv)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:779
← previousnext →201–300 of 1,003, ranked by callers