MCPcopy Create free account

hub / github.com/MeiGen-AI/MultiTalk / functions

Functions446 in github.com/MeiGen-AI/MultiTalk

⨍ Functions 446◇ Types & classes 101
Functioninit_weights
(m, mean=0.0, std=0.01)
kokoro/istftnet.py:11
Methodlist_loaded_loras
(self)
wan/wan_lora.py:109
Methodload_image
(self, data_key, **kwargs)
wan/utils/vace_processor.py:63
Methodload_image_pair
(self, data_key, data_key2, **kwargs)
wan/utils/vace_processor.py:66
Functionload_lora_for_models
(model, clip, lora, strength_model, strength_clip)
wan/utils/utils.py:331
Functionload_torch_file
(ckpt, safe_load=False, device=None, return_metadata=False)
wan/utils/utils.py:143
Methodmp_worker
(self, gpu, gpu_infer, pmi_rank, pmi_world_size, in_q_list, out_q, initialized_events, work_
wan/vace.py:562
Methodnoop_no_sync
()
wan/first_last_frame2video.py:279
Methodnoop_no_sync
()
wan/image2video.py:252
Methodnoop_no_sync
()
wan/text2video.py:198
Methodnoop_no_sync
()
wan/vace.py:394
Methodnoop_no_sync
()
wan/vace.py:683
Methodnoop_no_sync
()
wan/multitalk.py:586
Methodoffload
(self)
src/vram_management/layers.py:98
Methodoffload
(self)
src/vram_management/layers.py:157
Methodonload
(self)
src/vram_management/layers.py:105
Methodonload
(self)
src/vram_management/layers.py:165
Methodparam_groups
(self)
wan/modules/clip.py:418
Methodpred_dur
(self)
kokoro/pipeline.py:348
Functionprepare_source
(src_video, src_mask, src_ref_images, num_frames, image_size, device)
wan/utils/vace_processor.py:274
Methodprepare_source
(self, src_video, src_mask, src_ref_images, num_frames, image_size, device)
wan/vace.py:212
Functionprocess_vision_info
( conversations: list[dict] | list[list[dict]], )
wan/utils/qwen_vl_utils.py:344
Methodqkv_fn
(x)
wan/modules/multitalk_model.py:144
Methodqkv_fn
(x)
wan/modules/model.py:141
Functionregister_empty_buffer
(module, name, buffer, persistent=True)
src/utils.py:21
Functionregister_empty_parameter
(module, name, param)
src/utils.py:11
Methodsample
(self, imgs, deterministic=False)
wan/modules/vae.py:575
Methodscale_model_input
Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Ar
wan/utils/fm_solvers.py:802
Methodscale_model_input
Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. A
wan/utils/fm_solvers_unipc.py:743
Methodset_begin_index
Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_index
wan/utils/fm_solvers.py:218
Methodset_begin_index
Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_inde
wan/utils/fm_solvers_unipc.py:151
Methodset_timesteps
Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`):
wan/utils/fm_solvers_unipc.py:162
Functionshard_model
( model, device_id, param_dtype=torch.bfloat16, reduce_dtype=torch.float32, buffer_dtype=t
wan/distributed/fsdp.py:12
Functionstandardize_lora_key_format
(lora_sd)
wan/utils/utils.py:182
Methodstep_index
The index counter for current timestep. It will increase 1 after each scheduler step.
wan/utils/fm_solvers.py:204
Methodstep_index
The index counter for current timestep. It will increase 1 after each scheduler step.
wan/utils/fm_solvers_unipc.py:137
Functionstr2bool
Convert a string to a boolean. Supported true values: 'yes', 'true', 't', 'y', '1' Supported false values: 'no', 'false', 'f', 'n', '0'
wan/utils/utils.py:94
Functiontoggle_audio_mode
(mode)
app.py:636
Functionusp_attn_forward
(self, x, seq_lens, grid_sizes,
wan/distributed/xdit_context_parallel.py:184
Functionusp_attn_forward_multitalk
(self, x, seq_lens, grid_sizes,
wan/distributed/xdit_context_parallel.py:428
Functionusp_crossattn_multi_forward_multitalk
(self, x: torch.Tensor, enco
wan/distributed/xdit_context_parallel.py:474
Functionusp_dit_forward
x: A list of videos each with shape [C, T, H, W]. t: [B]. context: A list of text embeddings each with s
wan/distributed/xdit_context_parallel.py:99
Functionusp_dit_forward_multitalk
x: A list of videos each with shape [C, T, H, W]. t: [B]. context: A list of text embeddings each with s
wan/distributed/xdit_context_parallel.py:232
Functionusp_dit_forward_vace
(self, x, vace_context, seq_len, kwargs)
wan/distributed/xdit_context_parallel.py:74
Functionwrapper
(*args, **kwargs)
src/utils.py:27
Functionxlm_roberta_large
XLMRobertaLarge adapted from Huggingface.
wan/modules/xlm_roberta.py:146
← previous401–446 of 446, ranked by callers