Functions — github.com/billwuhao/ComfyUI

hub / github.com/billwuhao/ComfyUI_ACE-Step / functions

Functions348 in github.com/billwuhao/ComfyUI_ACE-Step

⨍ Functions 348◇ Types & classes 68

Methodgenerate

(self, **kwargs)

ace_step_nodes.py:139

MethodgetPriorityThreshold

(self)

ace_step/language_segmentation/LangSegment.py:730

Methodget_number_tokens

(self)

ace_step/ace_models/lyrics_utils/lyric_tokenizer.py:707

Methodgetfilters

(self)

ace_step/language_segmentation/LangSegment.py:724

Methodhook

(module, input, output)

ace_step/pipeline_ace_step.py:124

Functioninit_weights

(m, mean=0.0, std=0.01)

ace_step/music_dcae/music_vocoder.py:260

Methodkatsu

(self)

ace_step/ace_models/lyrics_utils/lyric_tokenizer.py:628

Methodload

(self, dcae_checkpoint, vocoder_checkpoint, ace_step_checkpoint, text_encoder_checkpoint, quantized=False, cpu

ace_step_nodes.py:208

Methodlogistic_function

(x, L=0.9, U=1.1, x_0=0.0, k=1)

ace_step/schedulers/scheduling_flow_match_euler_discrete.py:285

Methodlogistic_function

(x, L=0.9, U=1.1, x_0=0.0, k=1)

ace_step/schedulers/scheduling_flow_match_pingpong.py:285

Methodlogistic_function

(x, L=0.9, U=1.1, x_0=0.0, k=1)

ace_step/schedulers/scheduling_flow_match_heun_discrete.py:250

Methodlyricsgen

(self, multi_line_prompt: str)

ace_step_nodes.py:183

Methodlyricsgen

(self, lyrics: str, language: str, threshold: float)

text2lyric.py:130

Functionmake_pad_mask

Make mask tensor containing indices of padded part. See description of make_non_pad_mask. Args: lengths (torch.Tensor): Batch of len

ace_step/ace_models/lyrics_utils/lyric_encoder.py:875

MethodnonZero

(num,cn,func=None)

ace_step/language_segmentation/LangSegment.py:136

Functionnormalize_text

对文本进行标准化处理，去除标点符号，转为小写（如果适用）

ace_step/ace_models/lyrics_utils/lyric_normalizer.py:40

Methodposition_encoding

( self, offset: Union[int, torch.Tensor], size: int )

ace_step/ace_models/lyrics_utils/lyric_encoder.py:834

Methodpromptgen

(self, multi_line_prompt: str)

ace_step_nodes.py:162

Methodremove_weight_norm

(self)

ace_step/music_dcae/music_vocoder.py:478

Functionreplace_asmd

Args: match (re.Match) Returns: str

ace_step/language_segmentation/utils/num.py:125

Functionreplace_default_num

Args: match (re.Match) Returns: str

ace_step/language_segmentation/utils/num.py:100

Functionreplace_frac

Args: match (re.Match) Returns: str

ace_step/language_segmentation/utils/num.py:39

Functionreplace_negative_num

Args: match (re.Match) Returns: str

ace_step/language_segmentation/utils/num.py:80

Functionreplace_number

Args: match (re.Match) Returns: str

ace_step/language_segmentation/utils/num.py:195

Functionreplace_percentage

Args: match (re.Match) Returns: str

ace_step/language_segmentation/utils/num.py:60

Functionreplace_positive_quantifier

Args: match (re.Match) Returns: str

ace_step/language_segmentation/utils/num.py:177

Functionreplace_power

Args: match (re.Match) Returns: str

ace_step/language_segmentation/utils/num.py:155

Functionreplace_range

Args: match (re.Match) Returns: str

ace_step/language_segmentation/utils/num.py:227

Functionreplace_to_range

Args: match (re.Match) Returns: str

ace_step/language_segmentation/utils/num.py:245

Methodscale_noise

Forward process in flow-matching Args: sample (`torch.FloatTensor`): The input sample. times

ace_step/schedulers/scheduling_flow_match_euler_discrete.py:120

Methodscale_noise

Forward process in flow-matching Args: sample (`torch.FloatTensor`): The input sample.

ace_step/schedulers/scheduling_flow_match_pingpong.py:120

Methodscale_noise

Forward process in flow-matching Args: sample (`torch.FloatTensor`): The input sample. times

ace_step/schedulers/scheduling_flow_match_heun_discrete.py:113

MethodsetPriorityThreshold

(self, threshold:float)

ace_step/language_segmentation/LangSegment.py:727

Methodset_begin_index

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_inde

ace_step/schedulers/scheduling_flow_match_euler_discrete.py:110

Methodset_begin_index

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_

ace_step/schedulers/scheduling_flow_match_pingpong.py:110

Methodset_begin_index

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_inde

ace_step/schedulers/scheduling_flow_match_heun_discrete.py:103

Methodset_timesteps

Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`)

ace_step/schedulers/scheduling_flow_match_euler_discrete.py:176

Methodset_timesteps

Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`i

ace_step/schedulers/scheduling_flow_match_pingpong.py:176

Methodset_timesteps

Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`)

ace_step/schedulers/scheduling_flow_match_heun_discrete.py:143

Functionsplit_sentence

Preprocess the input text

ace_step/ace_models/lyrics_utils/lyric_tokenizer.py:37

Methodstate_in_first_order

(self)

ace_step/schedulers/scheduling_flow_match_heun_discrete.py:206

Methodstep

Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned m

ace_step/schedulers/scheduling_flow_match_euler_discrete.py:244

Methodstep

Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned m

ace_step/schedulers/scheduling_flow_match_heun_discrete.py:209

Methodstep_index

The index counter for current timestep. It will increase 1 after each scheduler step.

ace_step/schedulers/scheduling_flow_match_euler_discrete.py:96

Methodstep_index

The index counter for current timestep. It will increase 1 after each scheduler step.

ace_step/schedulers/scheduling_flow_match_pingpong.py:96

Methodstep_index

The index counter for current timestep. It will increase 1 after each scheduler step.

ace_step/schedulers/scheduling_flow_match_heun_discrete.py:89

Functionsubsequent_mask

Create mask for subsequent steps (size, size). This mask is used only in decoder which works in an auto-regressive mode. This means the curre

ace_step/ace_models/lyrics_utils/lyric_encoder.py:437

Functionwrapper

(self, *args, **kwargs)

ace_step/cpu_offload.py:30

← previous301–348 of 348, ranked by callers