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
↓ 3 callersMethodforward
(self, hidden_states)
VDM_Decoder/sgm/modules/diffusionmodules/lora.py:38
↓ 3 callersMethodforward
(self, x, space_only=False, time_only=False)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:485
↓ 3 callersFunctiongenerate_progress_cell
(value)
app.py:561
↓ 3 callersMethodget_input
(self, batch: Dict)
VDM_Decoder/vae_modules/autoencoder.py:192
↓ 3 callersFunctionget_model
Build the model.
VDM_Decoder/sgm/models/sat_ours/base_model.py:296
↓ 3 callersFunctionget_obj_from_str
(string, reload=False, invalidate_cache=True)
VDM_Decoder/sgm/util.py:264
↓ 3 callersFunctionget_obj_from_str
(string, reload=False, invalidate_cache=True)
VDM_Decoder/vae_modules/utils.py:258
↓ 3 callersFunctiongrad_layer_wrt_loss
(loss: Tensor, layer: nn.Parameter)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:149
↓ 3 callersFunctioninitialize_context_parallel
(context_parallel_size)
VDM_Decoder/vae_modules/utils.py:25
↓ 3 callersFunctionleaky_relu
(p=0.1)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:135
↓ 3 callersFunctionlog_txt_as_img
(wh, xc, size=10)
VDM_Decoder/sgm/util.py:156
↓ 3 callersFunctionmaybe_del_attr_
(o, attr)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:84
↓ 3 callersFunctionpad_at_dim
(t, pad, dim=-1, value=0.0)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:100
↓ 3 callersFunctionpair
(t)
VDM_Decoder/sgm/modules/autoencoding/losses/video_loss.py:29
↓ 3 callersMethodprepare_inputs
(self, x: torch.Tensor, s: float, c: Dict, uc: Dict)
VDM_Decoder/sgm/modules/diffusionmodules/guiders.py:18
↓ 3 callersFunctionreshape_tensor
(x, heads)
VDM_Decoder/sgm/modules/attention.py:80
↓ 3 callersMethodrotary
(self, t, **kwargs)
VDM_Decoder/dit_video_concat.py:370
↓ 3 callersMethodsampler_step
(self, sigma, next_sigma, denoiser, x, cond, uc=None, gamma=0.0)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:94
↓ 3 callersMethodupdate_input_embeds
(self, input_embeds, video_embeds_lm, ids_cmp_mask)
MLLM/src/models_clm/models.py:247
↓ 3 callersMethodupdate_input_embeds_face
(self, input_embeds,input_ids,video_embeds_lm)
MLLM/src/models_clm/models.py:288
↓ 2 callersFunctionNormalize
(in_channels)
VDM_Decoder/sgm/modules/attention.py:123
↓ 2 callersFunctionSameConv2d
(dim_in, dim_out, kernel_size)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:802
↓ 2 callersMethod__init__
(self, urls, seed, nshards=sys.maxsize, deterministic=True)
VDM_Decoder/sgm/webds.py:56
↓ 2 callersMethod__init__
(self, sigma_min=0.002, sigma_max=80.0, rho=7.0)
VDM_Decoder/sgm/modules/diffusionmodules/discretizer.py:33
↓ 2 callersMethod__init__
(self, embed_dim, n_classes=1000, key='class', ucg_rate=0.1)
VDM_Decoder/sgm/modules/encoders/ip_encoder.py:23
↓ 2 callersMethod__init__
(self)
VDM_Decoder/sgm/modules/encoders/modules.py:30
↓ 2 callersMethod__init__
( self, in_features, hidden_features=None, out_features=None, act_laye
MLLM/src/models/vit.py:12
↓ 2 callersFunction_drop_from_previous_rank
(input_, dim, kernel_size)
VDM_Decoder/vae_modules/cp_enc_dec.py:291
↓ 2 callersMethod_make_causal_mask
Make causal mask used for bi-directional self-attention.
MLLM/src/models/mistral/modeling_attn_mask_utils.py:108
↓ 2 callersMethod_set_cos_sin_cache
(self, seq_len, device, dtype)
MLLM/src/models/mistral/modeling_mistral.py:115
↓ 2 callersMethod_validation_step
(self, batch: dict, batch_idx: int, postfix: str = "")
VDM_Decoder/vae_modules/autoencoder.py:317
↓ 2 callersFunctionadd_model_config_args
Model arguments
VDM_Decoder/arguments.py:15
↓ 2 callersMethodadd_noise_to_first_frame
(self, image)
VDM_Decoder/diffusion_video.py:168
↓ 2 callersMethodancestral_euler_step
(self, x, denoised, sigma, sigma_down)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:169
↓ 2 callersMethodancestral_step
(self, x, sigma, next_sigma, sigma_up)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:175
↓ 2 callersMethodapply_ckpt
(self, ckpt: Union[None, str, dict])
VDM_Decoder/vae_modules/autoencoder.py:70
↓ 2 callersMethodbits_to_codes
(self, bits)
VDM_Decoder/sgm/modules/autoencoding/regularizers/lookup_free_quantization.py:138
↓ 2 callersFunctioncount_flops_attn
A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr
VDM_Decoder/sgm/modules/diffusionmodules/openaimodel.py:399
↓ 2 callersFunctiondefault
(*args)
VDM_Decoder/sgm/modules/autoencoding/regularizers/finite_scalar_quantization.py:23
↓ 2 callersMethodema_scope
(self, context=None)
VDM_Decoder/vae_modules/autoencoder.py:98
↓ 2 callersFunctionentropy
(prob)
VDM_Decoder/sgm/modules/autoencoding/regularizers/lookup_free_quantization.py:55
↓ 2 callersMethodeuler_step
(self, x, d, dt)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:81
↓ 2 callersFunctionexpand_dims_like
(x, y)
VDM_Decoder/sgm/util.py:227
↓ 2 callersMethodfind_in_interval
(self, n)
VDM_Decoder/sgm/lr_scheduler.py:62
↓ 2 callersMethodfrom_pretrained
(cls, llm, input_resampler, output_resampler, pretrained_model_path=None, **kwargs)
MLLM/src/models_clm/models.py:560
↓ 2 callersMethodgenerate
(self, tokenizer, prompt=None, input_ids=None,
MLLM/src/models_clm/models.py:380
↓ 2 callersMethodgenerate_bi
(self, tokenizer, prompt=None, input_ids=None,
MLLM/src/models_clm/models.py:471
↓ 2 callersFunctiongenerate_roughly_equally_spaced_steps
(num_substeps: int, max_step: int)
VDM_Decoder/sgm/modules/diffusionmodules/discretizer.py:11
↓ 2 callersFunctionget_2d_sincos_pos_embed
grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/
VDM_Decoder/dit_video_concat.py:175
↓ 2 callersFunctionget_2d_sincos_pos_embed_from_grid
(embed_dim, grid)
VDM_Decoder/dit_video_concat.py:193
↓ 2 callersFunctionget_ancestral_step
(sigma_from, sigma_to, eta=1.0)
VDM_Decoder/sgm/modules/diffusionmodules/sampling_utils.py:135
↓ 2 callersFunctionget_args
Parse all the args.
VDM_Decoder/arguments.py:59
↓ 2 callersMethodget_autoencoder_params
(self)
VDM_Decoder/vae_modules/autoencoder.py:198
↓ 2 callersFunctionget_ckpt_path
(name, root, check=False)
VDM_Decoder/sgm/modules/autoencoding/lpips/util.py:34
↓ 2 callersMethodget_input
(self, batch)
VDM_Decoder/diffusion_video.py:210
↓ 2 callersMethodget_last_layer
(self)
VDM_Decoder/vae_modules/autoencoder.py:215
↓ 2 callersMethodget_param_groups
( self, parameter_names: List[List[str]], optimizer_args: List[dict] )
VDM_Decoder/vae_modules/autoencoder.py:355
↓ 2 callersMethodget_sigmas
(self, n, device)
VDM_Decoder/sgm/modules/diffusionmodules/discretizer.py:28
↓ 2 callersMethodget_single_embedding
( self, embedder, batch, output, cond_or_not: Optional[np.ndarray] = N
VDM_Decoder/sgm/modules/encoders/modules.py:133
↓ 2 callersMethodget_trainable_parameters
(self)
VDM_Decoder/vae_modules/regularizers.py:68
↓ 2 callersMethodget_unconditional_conditioning
(self, bs, device="cuda")
VDM_Decoder/sgm/modules/encoders/ip_encoder.py:42
↓ 2 callersFunctiongrad_layer_wrt_loss
(loss: Tensor, layer: nn.Parameter)
VDM_Decoder/sgm/modules/autoencoding/losses/video_loss.py:47
↓ 2 callersFunctionhinge_discr_loss
(fake, real)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:139
↓ 2 callersFunctionhinge_gen_loss
(fake)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:143
↓ 2 callersMethodidx_to_sigma
(self, idx)
VDM_Decoder/sgm/modules/diffusionmodules/sigma_sampling.py:39
↓ 2 callersMethodinit_from_ckpt
(self, path, ignore_keys=list())
VDM_Decoder/vae_modules/autoencoder.py:564
↓ 2 callersMethodinitialize
(self, input)
VDM_Decoder/sgm/modules/autoencoding/lpips/util.py:56
↓ 2 callersMethodinstantiate_optimizer_from_config
(self, params, lr, cfg)
VDM_Decoder/vae_modules/autoencoder.py:120
↓ 2 callersFunctionis_odd
(n)
VDM_Decoder/sgm/modules/autoencoding/vqvae/movq_enc_3d.py:21
↓ 2 callersFunctionis_odd
(n)
VDM_Decoder/vae_modules/cp_enc_dec.py:34
↓ 2 callersFunctionmake_beta_schedule
( schedule, n_timestep, linear_start=1e-4, linear_end=2e-2, )
VDM_Decoder/sgm/modules/diffusionmodules/util.py:20
↓ 2 callersFunctionmd5_hash
(path)
VDM_Decoder/sgm/modules/autoencoding/lpips/util.py:28
↓ 2 callersFunctionnormalize_tensor
(x, eps=1e-10)
VDM_Decoder/sgm/modules/autoencoding/lpips/loss/lpips.py:126
↓ 2 callersMethodpossible_correction_step
(self, euler_step, x, d, dt, next_sigma, denoiser, cond, uc)
VDM_Decoder/sgm/modules/diffusionmodules/sampling.py:236
↓ 2 callersMethodreinit
(self, parent_model=None)
VDM_Decoder/sgm/models/sat_ours/base_model.py:47
↓ 2 callersMethodremap_to_used
(self, inds: torch.Tensor)
VDM_Decoder/sgm/modules/autoencoding/regularizers/quantize.py:26
↓ 2 callersFunctionrotate_half
Rotates half the hidden dims of the input.
MLLM/src/models/mistral/modeling_mistral.py:137
↓ 2 callersFunctionsafe_get_index
(it, ind, default=None)
VDM_Decoder/sgm/modules/autoencoding/magvit2_pytorch.py:50
↓ 2 callersMethodsigma_to_idx
(self, sigma)
VDM_Decoder/sgm/modules/diffusionmodules/denoiser.py:58
↓ 2 callersMethodto_4d
( self, attention_mask_2d: torch.Tensor, query_length: int, dtype: torch.dtype
MLLM/src/models/mistral/modeling_attn_mask_utils.py:67
↓ 2 callersMethodto_causal_4d
( self, batch_size: int, query_length: int, key_value_length: int, dty
MLLM/src/models/mistral/modeling_attn_mask_utils.py:37
↓ 2 callersMethodunmap_to_all
(self, inds: torch.Tensor)
VDM_Decoder/sgm/modules/autoencoding/regularizers/quantize.py:41
↓ 2 callersFunctionunpack_one
(t, ps, pattern)
VDM_Decoder/sgm/modules/autoencoding/regularizers/lookup_free_quantization.py:44
↓ 2 callersFunctionunpack_one
(t, ps, pattern)
VDM_Decoder/sgm/modules/autoencoding/regularizers/finite_scalar_quantization.py:34
↓ 2 callersFunctionzero_module
Zero out the parameters of a module and return it.
VDM_Decoder/sgm/modules/attention.py:114
↓ 1 callersFunctionNormalize
(in_channels, gather=False, **kwargs)
VDM_Decoder/vae_modules/cp_enc_dec.py:444
↓ 1 callersFunctionNormalize3D
( in_channels, zq_ch, add_conv, gather=False, )
VDM_Decoder/vae_modules/cp_enc_dec.py:513
↓ 1 callersFunctionPerceiveFeedForward
(dim, mult=4)
VDM_Decoder/sgm/modules/attention.py:468
↓ 1 callersMethod__init__
( self, dim, n_heads, d_head, dropout=0.0, context_dim=None,
VDM_Decoder/sgm/modules/video_attention.py:21
↓ 1 callersMethod__init__
(self, block_scale=None, block_size=None, min_snr_value=None, fixed_frames=0, **kwargs)
VDM_Decoder/sgm/modules/diffusionmodules/loss.py:68
↓ 1 callersMethod__init__
(self, weighting_config, scaling_config)
VDM_Decoder/sgm/modules/diffusionmodules/denoiser.py:10
↓ 1 callersMethod__init__
(self, scale, dyn_thresh_config=None)
VDM_Decoder/sgm/modules/diffusionmodules/guiders.py:27
↓ 1 callersMethod__init__
( self, num_hiddens, embedding_dim, n_embed, straight_through=True,
VDM_Decoder/sgm/modules/autoencoding/vqvae/quantize.py:137
↓ 1 callersMethod__init__
(self)
VDM_Decoder/sgm/models/sat_ours/base_model.py:43
↓ 1 callersMethod__init__
(self)
VDM_Decoder/vae_modules/regularizers.py:61
↓ 1 callersMethod__init__
(self, tokenizer, num_vid_gen_tokens=100)
MLLM/src/models_clm/generation.py:15
↓ 1 callersMethod_build_modules
(self, module_configs)
VDM_Decoder/dit_video_concat.py:768
↓ 1 callersMethod_expand_mask
Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
MLLM/src/models/mistral/modeling_attn_mask_utils.py:161
↓ 1 callersFunction_fake_cp_pass_from_previous_rank
(input_, dim, kernel_size, cache_padding=None)
VDM_Decoder/vae_modules/cp_enc_dec.py:241
↓ 1 callersMethod_flash_attention_forward
Calls the forward method of Flash Attention - if the input hidden states contain at least one padding token first unpad the input, th
MLLM/src/models/mistral/modeling_mistral.py:458
← previousnext →101–200 of 1,003, ranked by callers