MCPcopy Create free account

hub / github.com/MotrixLab/ViMoGen / functions

Functions457 in github.com/MotrixLab/ViMoGen

Method__init__
(self, dim, num_heads, window_size=(-1, -1),
models/transformer/wan/modules/t2m_model.py:336
Method__init__
(self, cross_attn_type, dim, ffn_dim, num_
models/transformer/wan/modules/t2m_model.py:386
Method__init__
(self, in_dim, out_dim)
models/transformer/wan/modules/t2m_model.py:481
Method__init__
(self, d_model, max_len=5000)
models/transformer/wan/modules/t2m_model.py:494
Method__init__
(self, model_type='t2v', patch_size=(1, 2, 2), text_len=512
models/transformer/wan/modules/t2m_model.py:515
Method__init__
(self)
models/transformer/wan/modules/t2m_model.py:710
Method__iter__
(self)
datasets/multi_resolution_sampler.py:151
Method__iter__
(self)
datasets/sampler.py:41
Method__iter__
(self)
datasets/sampler.py:91
Method__len__
(self, )
trainer/__init__.py:26
Method__len__
(self)
datasets/bucket.py:142
Method__len__
(self, )
datasets/multi_resolution_sampler.py:148
Method__len__
(self)
datasets/sampler.py:47
Method__len__
(self)
datasets/sampler.py:210
Method__len__
(self)
datasets/video_datasets.py:81
Method__len__
(self)
datasets/video_datasets.py:318
Method__len__
(self)
models/transformer/wan/text_encoding_batch.py:33
Method__lt__
(self, other)
datasets/bucket_config.py:123
Method__lt__
(self, other)
datasets/bucket_config.py:153
Method__lt__
(self, other)
datasets/bucket_config.py:185
Method__str__
(self)
datasets/bucket_config.py:162
Method__str__
(self)
datasets/bucket_config.py:194
Method_resolve_prompt_embedding
(self, data)
datasets/video_datasets.py:217
Method_sort_key
(rec: Dict[str, Any])
mbench/__init__.py:412
Methodadd_figure
(self, tag, figure, **kwargs)
parallel/logging.py:103
Methodadd_text
(self, tag, text_string, **kwargs)
parallel/logging.py:99
Functionapply
(data, method=None, frame_interval=None, seed=None, num_bucket=None)
datasets/sampler.py:17
Functionattention
( q, k, v, q_lens=None, k_lens=None, dropout_p=0., softmax_scale=None, q_scale
models/transformer/wan/modules/tm2m_model.py:164
Functionattention
( q, k, v, q_lens=None, k_lens=None, dropout_p=0., softmax_scale=None, q_scale
models/transformer/wan/modules/attention.py:133
Functionattention
( q, k, v, q_lens=None, k_lens=None, dropout_p=0., softmax_scale=None, q_scale
models/transformer/wan/modules/t2m_model.py:163
Functioncall_gemini
(client, video_path: Path, prompt: str, fps: int = 5)
motion_gating/apply_quality_gate.py:187
Functioncloset_smaller_bucket
(value, bucket)
datasets/bucket.py:146
Functioncollate_fn_default
(batch)
datasets/dataloader.py:88
Functioncollate_fn_motion_wanvideo
(batch)
datasets/dataloader.py:109
Functioncompute_body_penetration
Compute body penetration/collision percentage using BVH collision detection
mbench/pose_quality.py:139
Functioncompute_dynamic_degree
Compute the dynamic degree of the motion based on the average velocity of the joints.
mbench/motion_quality.py:406
Functioncompute_foot_floating
Check for foot floating in the motion data.
mbench/motion_quality.py:212
Functioncompute_foot_sliding
Check for foot sliding in the motion data.
mbench/motion_quality.py:362
Functioncompute_ground_penetration
Compute foot-floor penetration based on the foot joints.
mbench/motion_quality.py:172
Functioncompute_jitter_degree
Compute the jitter degree of the motion based on the acceleration of the joints.
mbench/motion_quality.py:127
Functioncompute_motion_condition_consistency
Compute action accuracy for motion videos using Gemini API Args: full_info_path: Path to JSON file with video information
mbench/motion_condition_consistency.py:25
Functioncompute_motion_generalizability
Compute action accuracy for motion videos using Gemini API Args: full_info_path: Path to JSON file with video information
mbench/motion_generalizability.py:25
Functioncompute_pose_quality
(full_info_path: str, device: str, **kwargs)
mbench/pose_quality.py:93
Functioncount_trainable_parameters
(named_parameters)
models/transformer/wan/modules/utils.py:91
Methodcreate_custom_forward
(module)
models/transformer/wan/modules/tm2m_model.py:672
Methodcreate_custom_forward
(module)
models/transformer/wan/modules/t2m_model.py:657
Functioncreate_sdpa_mask
(q, k, q_lens, k_lens, causal=False)
models/transformer/wan/modules/tm2m_model.py:144
Functioncreate_sdpa_mask
(q, k, q_lens, k_lens, causal=False)
models/transformer/wan/modules/t2m_model.py:143
Functioncreate_video_info_dict
Create a video information dictionary Args: video_path: Path to the video file prompt: Text prompt associated with the v
mbench/utils.py:81
Methodcross_attn_ffn
(x, context, context_lens, e)
models/transformer/wan/modules/t2m_model.py:443
Methodcustom_forward
(*inputs, **kwargs)
models/transformer/wan/modules/tm2m_model.py:673
Methodcustom_forward
(*inputs, **kwargs)
models/transformer/wan/modules/t2m_model.py:658
Functiondummy_dataloader_for_debug
(batch_size: int = 4, num_workers: int = 4)
trainer/__init__.py:10
Methodelapsed_time
(self)
trainer/base_trainer.py:369
Functionensure_directory_exists
Ensure that a directory exists, creating it if necessary Args: path: Directory path to create
mbench/utils.py:133
Functionevaluate
(args)
mbench/cli/evaluate.py:55
Functionevaluate_entry
(prompt_dict)
mbench/motion_condition_consistency.py:65
Functionevaluate_entry
(prompt_dict)
mbench/motion_generalizability.py:65
Functionexecute_on_main_process
(self, *args, **kwargs)
parallel/utils.py:23
Functionfind_approximate_hw
(hw, hw_dict, approx=0.8)
datasets/bucket.py:8
Functionfind_closet_smaller_bucket
(t, t_dict, frame_interval)
datasets/bucket.py:15
Functionformat_results_summary
Format evaluation results into a readable summary string Args: results_dict: Dictionary containing evaluation results
mbench/utils.py:100
Methodforward
(self, x)
models/transformer/wan/modules/t5.py:48
Methodforward
(self, x)
models/transformer/wan/modules/t5.py:61
Methodforward
x: [B, L1, C]. context: [B, L2, C] or None. mask: [B, L2] or [B, L1, L2] or None.
models/transformer/wan/modules/t5.py:86
Methodforward
(self, x)
models/transformer/wan/modules/t5.py:136
Methodforward
(self, x, mask=None, pos_bias=None)
models/transformer/wan/modules/t5.py:170
Methodforward
(self, x, mask=None, encoder_states=None, enco
models/transformer/wan/modules/t5.py:206
Methodforward
(self, lq, lk)
models/transformer/wan/modules/t5.py:233
Methodforward
(self, ids, mask=None)
models/transformer/wan/modules/t5.py:303
Methodforward
(self, ids, mask=None, encoder_states=None, encoder_mask=None)
models/transformer/wan/modules/t5.py:351
Methodforward
(self, encoder_ids, encoder_mask, decoder_ids, decoder_mask)
models/transformer/wan/modules/t5.py:408
Methodforward
(self, x)
models/transformer/wan/modules/tm2m_model.py:243
Methodforward
(self, x)
models/transformer/wan/modules/tm2m_model.py:255
Methodforward
(self, x, seq_lens, freqs)
models/transformer/wan/modules/tm2m_model.py:284
Methodforward
x: [B, L1, C]. context: [B, L2, C]. context_lens: [B].
models/transformer/wan/modules/tm2m_model.py:311
Methodforward
( self, x, e, seq_lens, freqs, context, contex
models/transformer/wan/modules/tm2m_model.py:382
Methodforward
( self, x, e, seq_lens, freqs, )
models/transformer/wan/modules/tm2m_model.py:469
Methodforward
(self, image_embeds)
models/transformer/wan/modules/tm2m_model.py:531
Methodforward
(self, x)
models/transformer/wan/modules/tm2m_model.py:548
Methodforward
x: motion latents of shape [B, T, C]. x_mask: mask of shape [B, T], 1 for valid, 0 for invalid. t:
models/transformer/wan/modules/tm2m_model.py:650
Methodforward
(self, x)
models/transformer/wan/modules/t2m_model.py:242
Methodforward
(self, x)
models/transformer/wan/modules/t2m_model.py:254
Methodforward
(self, x, seq_lens, freqs)
models/transformer/wan/modules/t2m_model.py:283
Methodforward
x: [B, L1, C]. context: [B, L2, C]. context_lens: [B].
models/transformer/wan/modules/t2m_model.py:312
Methodforward
x: [B, L1, C]. context: [B, L2, C]. context_lens: [B].
models/transformer/wan/modules/t2m_model.py:350
Methodforward
( self, x, e, seq_lens, freqs, context, context_lens,
models/transformer/wan/modules/t2m_model.py:421
Methodforward
(self, image_embeds)
models/transformer/wan/modules/t2m_model.py:489
Methodforward
(self, x)
models/transformer/wan/modules/t2m_model.py:506
Methodforward
x: motion latents of shape [B, T, C]. x_mask: mask of shape [B, T], 1 for valid, 0 for invalid. t:
models/transformer/wan/modules/t2m_model.py:602
Methodfrom_civitai
(self, state_dict)
models/transformer/wan/modules/tm2m_model.py:796
Methodfrom_civitai
(self, state_dict)
models/transformer/wan/modules/t2m_model.py:716
Methodfrom_diffusers
(self, state_dict)
models/transformer/wan/modules/tm2m_model.py:793
Methodfrom_diffusers
(self, state_dict)
models/transformer/wan/modules/t2m_model.py:713
Functionfsdp_text_encoder
(model: nn.Module, device_mesh: DeviceMesh, dtype: torch.dtype)
parallel/parallel.py:23
Functionfsdp_transformer_ulysses
( model: nn.Module, device_mesh: DeviceMesh, global_device_mesh: DeviceMesh, dtype: torch.dtyp
parallel/parallel.py:50
Functionget_aspect_ratios_dict
(ars, ts=360 * 640)
datasets/aspect.py:15
Methodget_bucket_id
(self, T, H, W, frame_interval=1, seed=None)
datasets/bucket.py:81
Functionget_cfg_scale_list
(cfg_scale, enable_cfg_interval, timesteps: torch.Tensor,
trainer/scheduler.py:143
Functionget_cogvideo_dynamic_cfg_scale_list
(cfg_scale, num_inference_steps, timesteps)
trainer/scheduler.py:130
← previousnext →301–400 of 457, ranked by callers