Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/MeiGen-AI/InfiniteTalk
/ functions
Functions
460 in github.com/MeiGen-AI/InfiniteTalk
⨍
Functions
460
◇
Types & classes
102
Method
__init__
(self, style_dim, d_hid, nlayers, max_dur=50, dropout=0.1)
kokoro/modules.py:92
Method
__init__
(self, sty_dim, d_model, nlayers, dropout=0.1)
kokoro/modules.py:138
Method
__init__
(self, kmodel: KModel)
kokoro/model.py:144
Method
__init__
(self, config: Wav2Vec2Config)
src/audio_analysis/wav2vec2.py:10
Method
__init__
( self, module: qlinear.QLinear, offload_dtype, offload_device, onload
src/vram_management/layers.py:73
Method
__init__
( self, module: torch.nn.Linear, offload_dtype, offload_device, onload
src/vram_management/layers.py:129
Method
__iter__
(self)
kokoro/pipeline.py:352
Method
__len__
(self)
wan/utils/fm_solvers.py:858
Method
__len__
(self)
wan/utils/fm_solvers_unipc.py:801
Method
__len__
(self)
kokoro/pipeline.py:360
Function
_read_video_decord
read video using decord.VideoReader Args: ele (dict): a dict contains the configuration of video. support keys: - vid
wan/utils/qwen_vl_utils.py:221
Function
_read_video_torchvision
read video using torchvision.io.read_video Args: ele (dict): a dict contains the configuration of video. support keys:
wan/utils/qwen_vl_utils.py:177
Method
_sigma_to_t
(self, sigma)
wan/utils/fm_solvers.py:332
Method
_sigma_to_t
(self, sigma)
wan/utils/fm_solvers_unipc.py:271
Method
add_custom_field
(self, key: str, value)
wan/utils/prompt_extend.py:160
Method
add_noise
( self, original_samples: torch.Tensor, noise: torch.Tensor, timesteps: torch.
wan/utils/fm_solvers.py:817
Method
add_noise
( self, original_samples: torch.Tensor, noise: torch.Tensor, timesteps: torch.
wan/utils/fm_solvers_unipc.py:760
Function
attention
( q, k, v, q_lens=None, k_lens=None, dropout_p=0., softmax_scale=None, q_scale
wan/modules/attention.py:142
Method
audio
(self)
kokoro/pipeline.py:344
Method
begin_index
The index for the first timestep. It should be set from pipeline with `set_begin_index` method.
wan/utils/fm_solvers.py:211
Method
begin_index
The index for the first timestep. It should be set from pipeline with `set_begin_index` method.
wan/utils/fm_solvers_unipc.py:144
Function
cache_image
(tensor, save_file, nrow=8, normalize=True, va
wan/utils/utils.py:98
Function
cache_video
(tensor, save_file=None, fps=30, suffix='.mp4',
wan/utils/utils.py:57
Method
cross_attn_ffn
(x, context, context_lens, e)
wan/modules/model.py:309
Method
encode
( self, extract_features, attention_mask=None, mask_time_indices=None,
src/audio_analysis/wav2vec2.py:78
Method
ensure_image
(_image)
wan/utils/prompt_extend.py:297
Method
extend
(self, prompt, system_prompt, seed=-1, *args, **kwargs)
wan/utils/prompt_extend.py:252
Method
extend
(self, prompt, system_prompt, seed=-1, *args, **kwargs)
wan/utils/prompt_extend.py:433
Method
extend_with_img
(self, prompt, system_prompt, image: U
wan/utils/prompt_extend.py:288
Method
extend_with_img
(self, prompt, system_prompt, image: U
wan/utils/prompt_extend.py:464
Method
feature_extract
( self, input_values, seq_len, )
src/audio_analysis/wav2vec2.py:67
Method
forward
(self, x)
wan/modules/clip.py:43
Method
forward
(self, x)
wan/modules/clip.py:49
Method
forward
x: [B, L, C].
wan/modules/clip.py:74
Method
forward
(self, x)
wan/modules/clip.py:146
Method
forward
x: [B, L, C].
wan/modules/clip.py:186
Method
forward
(self, x, interpolation=False, use_31_block=False)
wan/modules/clip.py:279
Method
forward
(self, ids)
wan/modules/clip.py:315
Method
forward
imgs: [B, 3, H, W] of torch.float32. - mean: [0.48145466, 0.4578275, 0.40821073] - std: [0.26862954, 0.2613025
wan/modules/clip.py:406
Method
forward
(self, x)
wan/modules/t5.py:66
Method
forward
x: [B, L1, C]. context: [B, L2, C] or None. mask: [B, L2] or [B, L1, L2] or None.
wan/modules/t5.py:91
Method
forward
(self, x)
wan/modules/t5.py:141
Method
forward
(self, x, mask=None, pos_bias=None)
wan/modules/t5.py:175
Method
forward
(self, x, mask=None, encoder_states=None, enco
wan/modules/t5.py:211
Method
forward
(self, lq, lk)
wan/modules/t5.py:238
Method
forward
(self, ids, mask=None)
wan/modules/t5.py:308
Method
forward
(self, ids, mask=None, encoder_states=None, encoder_mask=None)
wan/modules/t5.py:356
Method
forward
(self, encoder_ids, encoder_mask, decoder_ids, decoder_mask)
wan/modules/t5.py:413
Method
forward
(self, x, cache_x=None)
wan/modules/vae.py:28
Method
forward
(self, x)
wan/modules/vae.py:51
Method
forward
Fix bfloat16 support for nearest neighbor interpolation.
wan/modules/vae.py:59
Method
forward
(self, x, feat_cache=None, feat_idx=[0])
wan/modules/vae.py:101
Method
forward
(self, x, feat_cache=None, feat_idx=[0])
wan/modules/vae.py:202
Method
forward
(self, x)
wan/modules/vae.py:240
Method
forward
(self, x, feat_cache=None, feat_idx=[0])
wan/modules/vae.py:318
Method
forward
(self, x, feat_cache=None, feat_idx=[0])
wan/modules/vae.py:423
Method
forward
r""" Args: x(Tensor): Shape [B, L, C]
wan/modules/multitalk_model.py:87
Method
forward
(self, inputs: torch.Tensor)
wan/modules/multitalk_model.py:103
Method
forward
(self, x, seq_lens, grid_sizes, freqs, ref_target_masks=None)
wan/modules/multitalk_model.py:140
Method
forward
(self, x, context, context_lens)
wan/modules/multitalk_model.py:189
Method
forward
( self, x, e, seq_lens, grid_sizes, freqs, context,
wan/modules/multitalk_model.py:274
Method
forward
r""" Args: x(Tensor): Shape [B, L1, C] e(Tensor): Shape [B, C]
wan/modules/multitalk_model.py:338
Method
forward
(self, image_embeds)
wan/modules/multitalk_model.py:361
Method
forward
(self, audio_embeds, audio_embeds_vf)
wan/modules/multitalk_model.py:396
Method
forward
( self, x, t, context, seq_len, clip_f
wan/modules/multitalk_model.py:598
Method
forward
(self, c, x, **kwargs)
wan/modules/vace_model.py:33
Method
forward
(self, x, hints, context_scale=1.0, **kwargs)
wan/modules/vace_model.py:58
Method
forward
(self, x: torch.Tensor, encoder_hidden_states: torch.Tensor,
wan/modules/attention.py:316
Method
forward
x: [B, L, C].
wan/modules/xlm_roberta.py:27
Method
forward
(self, x, mask)
wan/modules/xlm_roberta.py:66
Method
forward
ids: [B, L] of torch.LongTensor.
wan/modules/xlm_roberta.py:118
Method
forward
r""" Args: x(Tensor): Shape [B, L, C]
wan/modules/model.py:81
Method
forward
r""" Args: x(Tensor): Shape [B, L, C]
wan/modules/model.py:97
Method
forward
r""" Args: x(Tensor): Shape [B, L, num_heads, C / num_heads] seq_lens(Tensor): Shape [B] grid_sizes(Tensor
wan/modules/model.py:130
Method
forward
r""" Args: x(Tensor): Shape [B, L1, C] context(Tensor): Shape [B, L2, C] context_lens(Tensor): Shape [B]
wan/modules/model.py:164
Method
forward
r""" Args: x(Tensor): Shape [B, L1, C] context(Tensor): Shape [B, L2, C] context_lens(Tensor): Shape [B]
wan/modules/model.py:202
Method
forward
r""" Args: x(Tensor): Shape [B, L, C] e(Tensor): Shape [B, 6, C] seq_lens(Tensor): Shape [B], length of ea
wan/modules/model.py:278
Method
forward
(self, image_embeds)
wan/modules/model.py:363
Method
forward
r""" Forward pass through the diffusion model Args: x (List[Tensor]): List of input video tensors, each w
wan/modules/model.py:493
Method
forward
1D RoPE. Args: query (torch.tensor): [B, head, seq, head_dim] pos_indices (torch.tensor): [seq,] Returns:
wan/utils/multitalk_utils.py:173
Method
forward
(self, x, s)
kokoro/istftnet.py:27
Method
forward
(self, x, s)
kokoro/istftnet.py:68
Method
forward
(self, input_data)
kokoro/istftnet.py:102
Method
forward
sine_tensor, uv = forward(f0) input F0: tensor(batchsize=1, length, dim=1) f0 for unvoiced steps should be 0 output
kokoro/istftnet.py:185
Method
forward
Sine_source, noise_source = SourceModuleHnNSF(F0_sampled) F0_sampled (batchsize, length, 1) Sine_source (batchsize, length, 1
kokoro/istftnet.py:241
Method
forward
(self, x, s, f0)
kokoro/istftnet.py:299
Method
forward
(self, x)
kokoro/istftnet.py:333
Method
forward
(self, x, s)
kokoro/istftnet.py:378
Method
forward
(self, asr, F0_curve, N, s)
kokoro/istftnet.py:407
Method
forward
Full STFT -> iSTFT pass: returns time-domain reconstruction. Same interface as your original code.
kokoro/custom_stft.py:191
Method
forward
(self, x)
kokoro/modules.py:17
Method
forward
(self, x, input_lengths, m)
kokoro/modules.py:50
Method
forward
(self, x, s)
kokoro/modules.py:79
Method
forward
(self, texts, style, text_lengths, alignment, m)
kokoro/modules.py:109
Method
forward
(self, x, style, text_lengths, m)
kokoro/modules.py:148
Method
forward
(self, *args, **kwargs)
kokoro/modules.py:181
Method
forward
( self, phonemes: str, ref_s: torch.FloatTensor, speed: float = 1, ret
kokoro/model.py:125
Method
forward
( self, input_ids: torch.LongTensor, ref_s: torch.FloatTensor, speed: float =
kokoro/model.py:148
Method
forward
( self, input_values, seq_len, attention_mask=None, mask_time_indices=
src/audio_analysis/wav2vec2.py:13
Method
forward
(self, *args, **kwargs)
src/vram_management/layers.py:58
← previous
next →
301–400 of 460, ranked by callers