MCPcopy Create free account

hub / github.com/ali-vilab/TeaCache / functions

Functions1,040 in github.com/ali-vilab/TeaCache

⨍ Functions 1,040◇ Types & classes 227
↓ 1 callersFunctioneval_teacache_fast
(prompt_list)
eval/teacache/experiments/opensora_plan.py:571
↓ 1 callersFunctioneval_teacache_fast
(prompt_list)
eval/teacache/experiments/opensora.py:222
↓ 1 callersFunctioneval_teacache_slow
(prompt_list)
eval/teacache/experiments/latte.py:500
↓ 1 callersFunctioneval_teacache_slow
(prompt_list)
eval/teacache/experiments/cogvideox.py:194
↓ 1 callersFunctioneval_teacache_slow
(prompt_list)
eval/teacache/experiments/opensora_plan.py:560
↓ 1 callersFunctioneval_teacache_slow
(prompt_list)
eval/teacache/experiments/opensora.py:211
↓ 1 callersMethodexecute_method
(self, method: str, *args, **kwargs)
videosys/core/mp_utils.py:251
↓ 1 callersFunctionextract_json_from_prompts
(prompts, reference, mask_strategy)
videosys/pipelines/open_sora/pipeline_open_sora.py:719
↓ 1 callersFunctionextract_prompts_loop
(prompts, num_loop)
videosys/pipelines/open_sora/pipeline_open_sora.py:753
↓ 1 callersMethodfake_context_parallel_forward
(self, inputs: torch.Tensor)
videosys/models/autoencoders/autoencoder_kl_cogvideox.py:113
↓ 1 callersFunctionfetch_readme
This function reads the README.md file in the current directory. Returns: The lines in the README file.
setup.py:25
↓ 1 callersFunctionfetch_requirements
This function reads the requirements file. Args: path (str): the path to the requirements file. Returns: The lines in t
setup.py:9
↓ 1 callersMethodflash_attn_impl
(self, q, k, v, mask, B, N, C)
videosys/models/modules/attentions.py:136
↓ 1 callersMethodfrom_pretrained
(cls, pretrained_model_name_or_path: Optional[Union[str, os.PathLike]], **kwargs)
videosys/models/autoencoders/autoencoder_kl_open_sora_plan_v110.py:120
↓ 1 callersMethodfrom_pretrained
(cls, pretrained_model_name_or_path: Optional[Union[str, os.PathLike]], **kwargs)
videosys/models/autoencoders/autoencoder_kl_open_sora_plan_v120.py:184
↓ 1 callersMethodfuse_projections
(self, fuse=True)
videosys/models/modules/attentions.py:506
↓ 1 callersFunctiongather_from_second_dim
(x, batch_size, parallel_group)
videosys/core/comm.py:416
↓ 1 callersMethodgather_from_second_dim
(self, x, batch_size)
videosys/models/transformers/open_sora_plan_v110_transformer_3d.py:2787
↓ 1 callersMethodgather_from_second_dim
(self, x, batch_size)
videosys/models/transformers/open_sora_plan_transformer_3d.py:2782
↓ 1 callersFunctiongenerate
(args)
TeaCache4Wan2.1/teacache_generate.py:765
↓ 1 callersMethodgenerate
(self, *args, **kwargs)
videosys/core/pipeline.py:22
↓ 1 callersFunctionget_1d_sincos_pos_embed
(embed_dim, length, interpolation_scale=1.0, base_size=16)
videosys/models/transformers/open_sora_plan_v110_transformer_3d.py:109
↓ 1 callersFunctionget_1d_sincos_pos_embed
(embed_dim, length, interpolation_scale=1.0, base_size=16)
videosys/models/transformers/open_sora_plan_transformer_3d.py:122
↓ 1 callersMethodget_1d_sincos_temp_embed
(self, embed_dim, length)
videosys/models/transformers/latte_transformer_3d.py:1468
↓ 1 callersFunctionget_2d_sincos_pos_embed_from_grid
(embed_dim, grid)
videosys/models/transformers/open_sora_plan_v120_transformer_3d.py:190
↓ 1 callersFunctionget_2d_sincos_pos_embed_from_grid
(embed_dim, grid)
videosys/models/transformers/open_sora_plan_v110_transformer_3d.py:97
↓ 1 callersFunctionget_2d_sincos_pos_embed_from_grid
(embed_dim, grid)
videosys/models/transformers/open_sora_plan_transformer_3d.py:110
↓ 1 callersFunctionget_3d_rotary_pos_embed
RoPE for video tokens with 3D structure. Args: embed_dim: (`int`): The embedding dimension size, corresponding to hidden_size_he
videosys/models/modules/embeddings.py:283
↓ 1 callersFunctionget_3d_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/ or
videosys/models/transformers/open_sora_plan_v120_transformer_3d.py:121
↓ 1 callersFunctionget_3d_sincos_pos_embed_from_grid
(embed_dim, grid)
videosys/models/transformers/open_sora_plan_v120_transformer_3d.py:149
↓ 1 callersMethodget_cos_sin
(self, D, seq_len, device, dtype)
videosys/models/transformers/open_sora_plan_v110_transformer_3d.py:144
↓ 1 callersMethodget_cos_sin
(self, D, seq_len, device, dtype)
videosys/models/transformers/open_sora_plan_v110_transformer_3d.py:207
↓ 1 callersMethodget_cos_sin
(self, D, seq_len, device, dtype)
videosys/models/transformers/open_sora_plan_transformer_3d.py:157
↓ 1 callersMethodget_cos_sin
(self, D, seq_len, device, dtype)
videosys/models/transformers/open_sora_plan_transformer_3d.py:220
↓ 1 callersFunctionget_distributed_init_method
(ip: str, port: int)
videosys/core/mp_utils.py:32
↓ 1 callersFunctionget_image_size
(resolution, ar_ratio)
videosys/pipelines/open_sora/data_process.py:474
↓ 1 callersMethodget_mlp_output
(self, skip_range, timestep, block_idx, is_temporal=False)
videosys/core/pab_mgr.py:147
↓ 1 callersMethodget_mult
(self, h, r, alpha_prod_t, alpha_prod_t_prev, alpha_prod_t_back)
videosys/schedulers/scheduling_dpm_cogvideox.py:313
↓ 1 callersFunctionget_num_frames
(num_frames)
videosys/pipelines/open_sora/data_process.py:495
↓ 1 callersFunctionget_open_port
()
videosys/core/mp_utils.py:38
↓ 1 callersMethodget_processor
r""" Get the attention processor in use. Args: return_deprecated_lora (`bool`, *optional*, defaults to `False`):
videosys/models/transformers/open_sora_plan_transformer_3d.py:827
↓ 1 callersFunctionget_random_prompt_by_openai
()
videosys/pipelines/open_sora/pipeline_open_sora.py:921
↓ 1 callersFunctionget_resize_crop_region_for_grid
(src, tgt_width, tgt_height)
videosys/pipelines/cogvideox/pipeline_cogvideox.py:762
↓ 1 callersMethodget_text_embeddings
(self, texts)
videosys/pipelines/open_sora/pipeline_open_sora.py:269
↓ 1 callersFunctionget_transforms_image
(name="center", image_size=(256, 256))
videosys/pipelines/open_sora/data_process.py:699
↓ 1 callersFunctionget_transforms_video
(name="center", image_size=(256, 256))
videosys/pipelines/open_sora/data_process.py:543
↓ 1 callersMethodget_variables
(self, alpha_prod_t, alpha_prod_t_prev, alpha_prod_t_back=None)
videosys/schedulers/scheduling_dpm_cogvideox.py:300
↓ 1 callersFunctionget_video_ids
(gt_video_dirs, gen_video_dirs)
eval/teacache/common_metrics/batch_eval.py:65
↓ 1 callersFunctionget_videos
(video_ids, gt_video_dirs, gen_video_dirs)
eval/teacache/common_metrics/batch_eval.py:83
↓ 1 callersMethodif_broadcast_cross
(self, timestep: int, count: int)
videosys/core/pab_mgr.py:54
↓ 1 callersMethodif_broadcast_spatial
(self, timestep: int, count: int)
videosys/core/pab_mgr.py:80
↓ 1 callersMethodif_broadcast_temporal
(self, timestep: int, count: int)
videosys/core/pab_mgr.py:67
↓ 1 callersMethodif_skip_mlp
(self, timestep: int, count: int, block_idx: int, all_timesteps, is_temporal=False)
videosys/core/pab_mgr.py:108
↓ 1 callersFunctionimg_psnr
(img1, img2)
eval/teacache/common_metrics/calculate_psnr.py:7
↓ 1 callersFunctioninit_dist_logger
Update the logger to write to a log file.
videosys/utils/logging.py:15
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), remove_loss=False)
videosys/models/autoencoders/autoencoder_kl_open_sora_plan_v110.py:779
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list())
videosys/models/autoencoders/autoencoder_kl_open_sora_plan_v120.py:1051
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), remove_loss=False)
videosys/models/autoencoders/autoencoder_kl_open_sora_plan.py:779
↓ 1 callersMethodinitialize_weights
(self)
videosys/models/transformers/open_sora_transformer_3d.py:458
↓ 1 callersFunctionis_url
(url)
videosys/pipelines/open_sora/data_process.py:527
↓ 1 callersMethodkill_worker
(self)
videosys/core/mp_utils.py:268
↓ 1 callersFunctionmain
(args)
TeaCache4ConsisID/teacache_sample_video.py:199
↓ 1 callersFunctionmain
()
eval/teacache/common_metrics/calculate_psnr.py:75
↓ 1 callersFunctionmain
(args)
eval/teacache/common_metrics/eval.py:76
↓ 1 callersFunctionmain
()
eval/teacache/common_metrics/calculate_lpips.py:80
↓ 1 callersFunctionmain
(args)
eval/teacache/common_metrics/batch_eval.py:125
↓ 1 callersFunctionmain
()
eval/teacache/common_metrics/calculate_ssim.py:100
↓ 1 callersFunctionmain
()
TeaCache4HunyuanVideo/teacache_sample_video.py:199
↓ 1 callersFunctionmain
(args)
TeaCache4CogVideoX1.5/teacache_sample_video.py:186
↓ 1 callersMethodmake_position
(self, b, t, use_image_num, h, w, device)
videosys/models/transformers/open_sora_plan_v110_transformer_3d.py:2381
↓ 1 callersMethodmask_text_embeddings
(self, emb, mask)
videosys/pipelines/latte/pipeline_latte.py:278
↓ 1 callersMethodmask_text_embeddings
(self, emb, mask)
videosys/pipelines/open_sora_plan/pipeline_open_sora_plan.py:366
↓ 1 callersFunctionmerge_prompt
(text_list, loop_idx_list=None)
videosys/pipelines/open_sora/pipeline_open_sora.py:787
↓ 1 callersMethodmode
(self)
videosys/models/autoencoders/autoencoder_kl_open_sora_plan_v110.py:82
↓ 1 callersMethodmode
(self)
videosys/models/autoencoders/autoencoder_kl_open_sora_plan_v120.py:236
↓ 1 callersMethodmode
(self)
videosys/models/autoencoders/autoencoder_kl_open_sora_plan.py:82
↓ 1 callersMethodnorm_encoder_hidden_states
r""" Normalize the encoder hidden states. Requires `self.norm_cross` to be specified when constructing the `Attention` class.
videosys/models/transformers/open_sora_plan_v110_transformer_3d.py:1072
↓ 1 callersMethodnull_embed
(self, n)
videosys/pipelines/open_sora/pipeline_open_sora.py:294
↓ 1 callersFunctionpad_at_dim
(t, pad, dim=-1)
videosys/models/autoencoders/autoencoder_kl_open_sora.py:79
↓ 1 callersFunctionparse_args
()
eval/teacache/vbench/cal_vbench.py:91
↓ 1 callersFunctionparse_arguments
()
TeaCache4Cosmos/teacache_sample_video_i2v.py:300
↓ 1 callersFunctionparse_arguments
()
TeaCache4Cosmos/teacache_sample_video_t2v.py:256
↓ 1 callersFunctionparse_mask_strategy
(mask_strategy)
videosys/pipelines/open_sora/pipeline_open_sora.py:800
↓ 1 callersMethodpatchify_and_embed
(self, x)
videosys/models/transformers/vchitect_transformer_3d.py:483
↓ 1 callersMethodpostprocess
(self)
videosys/core/shardformer/t5/policy.py:67
↓ 1 callersMethodprecompute_freqs_cis
(dim: int, end: int, theta: float = 10000.0, rope_scaling_factor: float = 1.0)
videosys/models/transformers/vchitect_transformer_3d.py:341
↓ 1 callersMethodprepare_attention_mask
r""" Prepare the attention mask for the attention computation. Args: attention_mask (`torch.Tensor`): The
videosys/models/transformers/open_sora_plan_v120_transformer_3d.py:687
↓ 1 callersMethodprepare_attention_mask
r""" Prepare the attention mask for the attention computation. Args: attention_mask (`torch.Tensor`): The
videosys/models/transformers/open_sora_plan_v110_transformer_3d.py:1025
↓ 1 callersMethodprepare_extra_step_kwargs
(self, generator, eta)
videosys/pipelines/latte/pipeline_latte.py:448
↓ 1 callersMethodprepare_extra_step_kwargs
(self, generator, eta)
videosys/pipelines/cogvideox/pipeline_cogvideox.py:368
↓ 1 callersMethodprepare_extra_step_kwargs
(self, generator, eta)
videosys/pipelines/open_sora_plan/pipeline_open_sora_plan.py:676
↓ 1 callersMethodprepare_latents
( self, batch_size, num_channels_latents, video_length, height, width, dtype, device, generator, laten
videosys/pipelines/latte/pipeline_latte.py:649
↓ 1 callersMethodprepare_latents
( self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents
videosys/pipelines/cogvideox/pipeline_cogvideox.py:335
↓ 1 callersMethodprepare_latents
( self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents
videosys/pipelines/open_sora_plan/pipeline_open_sora_plan.py:888
↓ 1 callersMethodprepare_latents
( self, batch_size, num_channels_latents, height, width, frame
videosys/pipelines/vchitect/pipeline_vchitect.py:650
↓ 1 callersFunctionprepare_multi_resolution_info
(info_type, batch_size, image_size, num_frames, fps, device, dtype)
videosys/pipelines/open_sora/data_process.py:791
↓ 1 callersFunctionread_from_path
(path, image_size, transform_name="center")
videosys/pipelines/open_sora/data_process.py:770
↓ 1 callersFunctionread_image_from_path
(path, transform=None, transform_name="center", num_frames=1, image_size=(256, 256))
videosys/pipelines/open_sora/data_process.py:781
↓ 1 callersFunctionread_video_from_path
(path, transform=None, transform_name="center", image_size=(256, 256))
videosys/pipelines/open_sora/data_process.py:761
↓ 1 callersFunctionrefine_prompt_by_openai
(prompt)
videosys/pipelines/open_sora/pipeline_open_sora.py:931
← previousnext →301–400 of 1,040, ranked by callers