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
Function_split
(input_, dim)
VDM_Decoder/vae_modules/cp_enc_dec.py:76
Method_transpose_for_scores
Transpose a 3D tensor [b, s, np*hn] into a 4D tensor with size [b, np, s, hn].
VDM_Decoder/sgm/models/sat_ours/transformer.py:183
Method_unfuse_lora
(self)
VDM_Decoder/sgm/modules/diffusionmodules/lora.py:122
Method_unfuse_lora
(self)
VDM_Decoder/sgm/modules/diffusionmodules/lora.py:190
Method_update_scale
(self, scale)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:948
Functionall_gather
(tensor)
MLLM/src/train/dist_utils.py:5
Functionappend_dims
Appends dimensions to the end of a tensor until it has target_dims dimensions.
VDM_Decoder/sgm/util.py:278
Functionappend_dims
Appends dimensions to the end of a tensor until it has target_dims dimensions.
VDM_Decoder/vae_modules/utils.py:272
Functionappend_zero
(x)
VDM_Decoder/vae_modules/utils.py:268
Methodapply_ckpt
(self, ckpt: Union[None, str, dict])
VDM_Decoder/vae_modules/autoencoder.py:559
Methodattention_fn
( self, query_layer, key_layer, value_layer, attention_mask, a
VDM_Decoder/dit_video_concat.py:383
Methodattention_fn
( self, query_layer, key_layer, value_layer, attention_mask, a
VDM_Decoder/dit_video_concat.py:644
Functionattention_forward_default
(self, hidden_states, mask, backend=None, **kw_args)
VDM_Decoder/sgm/models/sat_ours/transformer_defaults.py:114
Functionautocast
(f, enabled=True)
VDM_Decoder/sgm/util.py:140
Functionautocast
(f, enabled=True)
VDM_Decoder/vae_modules/utils.py:134
Methodbackward
(ctx, *output_grads)
VDM_Decoder/sgm/modules/diffusionmodules/util.py:99
Methodbackward
(ctx, *output_grads)
VDM_Decoder/vae_modules/utils.py:389
Methodbackward
(ctx, grad_output)
VDM_Decoder/vae_modules/cp_enc_dec.py:304
Methodbackward
(ctx, grad_output)
VDM_Decoder/vae_modules/cp_enc_dec.py:316
Methodbackward
(ctx, grad_output)
VDM_Decoder/vae_modules/cp_enc_dec.py:328
Methodbackward
(ctx, grad_output)
VDM_Decoder/vae_modules/cp_enc_dec.py:340
Functionbert_tokenizer
(pretrained_model_name_or_path)
MLLM/src/processer/tokenizer.py:4
Functioncast_tuple
(t, length=1)
VDM_Decoder/sgm/modules/autoencoding/vqvae/movq_dec_3d.py:10
Functionconcat_all_gather
Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.
MLLM/src/train/dist_utils.py:21
Methodconfigure_optimizers
(self)
VDM_Decoder/vae_modules/autoencoder.py:124
Methodconfigure_optimizers
(self)
VDM_Decoder/vae_modules/autoencoder.py:375
Functionconv_pass_from_last_rank
(input_, dim, kernel_size)
VDM_Decoder/vae_modules/cp_enc_dec.py:352
Functionconvert_module_to_f16
(x)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:28
Functionconvert_module_to_f32
(x)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:32
Methodconvert_to_fp16
Convert the torso of the model to float16.
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:951
Methodconvert_to_fp16
Convert the torso of the model to float16.
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:1180
Methodconvert_to_fp32
Convert the torso of the model to float32.
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:959
Methodconvert_to_fp32
Convert the torso of the model to float32.
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:1187
Methodcopy_for_eval
(self)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:1340
Methodcount_flops
(model, _x, y)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:445
Methodcount_flops
(model, _x, y)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:479
Functioncount_params
(model, verbose=False)
VDM_Decoder/vae_modules/utils.py:241
Functioncross_attention_forward_default
(self, hidden_states, cross_attention_mask, encoder_outputs, **kw_args)
VDM_Decoder/sgm/models/sat_ours/transformer_defaults.py:167
Methodcustom
(start, end, kw_args_index, cross_layer_index)
VDM_Decoder/sgm/models/sat_ours/transformer.py:625
Methodcustom_forward
(*inputs)
VDM_Decoder/sgm/models/sat_ours/transformer.py:626
Methoddecode
(self, *args, **kwargs)
VDM_Decoder/vae_modules/autoencoder.py:117
Methoddecode
(self, z: torch.Tensor, **decoder_kwargs)
VDM_Decoder/vae_modules/autoencoder.py:484
Methoddecode
(self, x: Any, *args, **kwargs)
VDM_Decoder/vae_modules/autoencoder.py:522
Methoddecode_from_code_indices
(self, codes: Tensor, cond: Optional[Tensor] = None, video_contains_first_frame=True)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:1434
Methoddel_mixin
(self, name)
VDM_Decoder/sgm/models/sat_ours/base_model.py:117
Methoddenoise
(self, x, denoiser, sigma, cond, uc)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:57
Methoddisable_untrainable_params
NEW TRAINABLE MODULE
VDM_Decoder/diffusion_video.py:94
Methoddisable_untrainable_params
(self)
VDM_Decoder/sgm/models/sat_ours/base_model.py:170
Functiondisabled_train
Overwrite model.train with this function to make sure train/eval mode does not change anymore.
VDM_Decoder/sgm/util.py:102
Functiondisabled_train
Overwrite model.train with this function to make sure train/eval mode does not change anymore.
VDM_Decoder/sgm/modules/encoders/ip_encoder.py:49
Functiondisabled_train
Overwrite model.train with this function to make sure train/eval mode does not change anymore.
VDM_Decoder/vae_modules/utils.py:96
Methoddiscr_parameters
(self)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:1337
Functiondo_autocast
(*args, **kwargs)
VDM_Decoder/sgm/util.py:141
Functiondo_autocast
(*args, **kwargs)
VDM_Decoder/vae_modules/utils.py:135
Methoddtype
(self)
VDM_Decoder/sgm/modules/autoencoding/regularizers/lookup_free_quantization.py:142
Functiondynamic_threshold
(x, p=0.95)
VDM_Decoder/sgm/modules/diffusionmodules/sampling_utils.py:21
Functiondynamic_thresholding2
(x0)
VDM_Decoder/sgm/modules/diffusionmodules/sampling_utils.py:33
Functiondynamic_thresholding3
(x0)
VDM_Decoder/sgm/modules/diffusionmodules/sampling_utils.py:53
Methodencode
(self, *args, **kwargs)
VDM_Decoder/sgm/modules/encoders/ip_encoder.py:13
Methodencode
(self, x)
VDM_Decoder/sgm/modules/encoders/ip_encoder.py:18
Methodencode
(self, *args, **kwargs)
VDM_Decoder/vae_modules/autoencoder.py:113
Methodencode
(self, x: torch.Tensor, return_reg_log: bool = False)
VDM_Decoder/vae_modules/autoencoder.py:464
Methodencode
(self, x: Any, *args, **kwargs)
VDM_Decoder/vae_modules/autoencoder.py:519
Functionexists
(v)
VDM_Decoder/vae_modules/cp_enc_dec.py:38
Functionexpand_dims_like
(x, y)
VDM_Decoder/vae_modules/utils.py:221
Functionextract_into_tensor
(a, t, x_shape)
VDM_Decoder/sgm/modules/diffusionmodules/util.py:31
Methodfinal_forward
(self, logits, **kwargs)
VDM_Decoder/dit_video_concat.py:459
Functionfinal_forward_default
(self, logits, **kw_args)
VDM_Decoder/sgm/models/sat_ours/transformer_defaults.py:271
Methodforward
(self, x, batch)
VDM_Decoder/diffusion_video.py:161
Methodforward
(self, x, timesteps=None, context=None, ip_context=None, face_id_cond=None, y=None, **kwargs)
VDM_Decoder/dit_video_concat.py:891
Methodforward
(self, input)
VDM_Decoder/sgm/util.py:80
Methodforward
(self, x, context=None, timesteps=None)
VDM_Decoder/sgm/modules/video_attention.py:8
Methodforward
(self, x: torch.Tensor, context: torch.Tensor = None, timesteps: int = None)
VDM_Decoder/sgm/modules/video_attention.py:99
Methodforward
( self, x: torch.Tensor, context: Optional[torch.Tensor] = None, time_context:
VDM_Decoder/sgm/modules/video_attention.py:227
Methodforward
(self, model)
VDM_Decoder/sgm/modules/ema.py:31
Methodforward
(self, x)
VDM_Decoder/sgm/modules/attention.py:96
Methodforward
(self, x)
VDM_Decoder/sgm/modules/attention.py:110
Methodforward
(self, x)
VDM_Decoder/sgm/modules/attention.py:135
Methodforward
(self, x)
VDM_Decoder/sgm/modules/attention.py:157
Methodforward
( self, x, context=None, mask=None, additional_tokens=None, n_
VDM_Decoder/sgm/modules/attention.py:207
Methodforward
( self, x, context=None, mask=None, additional_tokens=None, n_
VDM_Decoder/sgm/modules/attention.py:292
Methodforward
( self, x, context=None, mask=None, additional_tokens=None, n_
VDM_Decoder/sgm/modules/attention.py:381
Methodforward
Args: x (torch.Tensor): image features shape (b, n1, D) latent (torch.Tensor): latent features
VDM_Decoder/sgm/modules/attention.py:437
Methodforward
(self, latents=None, x=None)
VDM_Decoder/sgm/modules/attention.py:506
Methodforward
( self, x, context=None, mask=None, additional_tokens=None, n_
VDM_Decoder/sgm/modules/attention.py:542
Methodforward
(self, x, context=None, additional_tokens=None, n_times_crossframe_attn_in_self=0)
VDM_Decoder/sgm/modules/attention.py:667
Methodforward
(self, x, context=None)
VDM_Decoder/sgm/modules/attention.py:730
Methodforward
(self, x, context=None)
VDM_Decoder/sgm/modules/attention.py:814
Methodforward
(self, x)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:55
Methodforward
Apply the module to `x` given `emb` timestep embeddings.
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:72
Methodforward
( self, x: th.Tensor, emb: th.Tensor, context: Optional[th.Tensor] = None,
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:84
Methodforward
(self, x)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:162
Methodforward
(self, x)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:202
Methodforward
Apply the block to a Tensor, conditioned on a timestep embedding. :param x: an [N x C x ...] Tensor of features. :param emb:
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:309
Methodforward
(self, x, **kwargs)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:383
Methodforward
Apply QKV attention. :param qkv: an [N x (H * 3 * C) x T] tensor of Qs, Ks, and Vs. :return: an [N x (H * C) x T] tensor afte
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:428
Methodforward
Apply QKV attention. :param qkv: an [N x (3 * H * C) x T] tensor of Qs, Ks, and Vs. :return: an [N x (H * C) x T] tensor afte
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:458
Methodforward
(self, t)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:488
Methodforward
Apply the model to an input batch. :param x: an [N x C x ...] Tensor of inputs. :param timesteps: a 1-D batch of timesteps.
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:967
Methodforward
(self, x, timesteps=None, context=None, y=None, **kwargs)
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:1004
← previousnext →601–700 of 1,003, ranked by callers