wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-03-30 13:33:42 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Merge 6a2ceb470b into a500f1edac

Browse Source
This commit is contained in:
Mark Ledford 2026-03-29 10:52:05 +00:00 committed by GitHub
commit b7bba4a57c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 192 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

213
comfy_extras/nodes_ace.py
View File

@ -16,7 +16,9 @@ class TextEncodeAceStepAudio(io.ComfyNode):
io.Clip.Input("clip"),
io.String.Input("tags", multiline=True, dynamic_prompts=True),
io.String.Input("lyrics", multiline=True, dynamic_prompts=True),
io.Float.Input("lyrics_strength", default=1.0, min=0.0, max=10.0, step=0.01),
io.Float.Input(
"lyrics_strength", default=1.0, min=0.0, max=10.0, step=0.01
),
],
outputs=[io.Conditioning.Output()],
)
@ -25,9 +27,12 @@ class TextEncodeAceStepAudio(io.ComfyNode):
def execute(cls, clip, tags, lyrics, lyrics_strength) -> io.NodeOutput:
tokens = clip.tokenize(tags, lyrics=lyrics)
conditioning = clip.encode_from_tokens_scheduled(tokens)
conditioning = node_helpers.conditioning_set_values(conditioning, {"lyrics_strength": lyrics_strength})
conditioning = node_helpers.conditioning_set_values(
conditioning, {"lyrics_strength": lyrics_strength}
)
return io.NodeOutput(conditioning)
class TextEncodeAceStepAudio15(io.ComfyNode):
@classmethod
def define_schema(cls):
@ -38,25 +43,168 @@ class TextEncodeAceStepAudio15(io.ComfyNode):
io.Clip.Input("clip"),
io.String.Input("tags", multiline=True, dynamic_prompts=True),
io.String.Input("lyrics", multiline=True, dynamic_prompts=True),
io.Int.Input("seed", default=0, min=0, max=0xffffffffffffffff, control_after_generate=True),
io.Int.Input(
"seed",
default=0,
min=0,
max=0xFFFFFFFFFFFFFFFF,
control_after_generate=True,
),
io.Int.Input("bpm", default=120, min=10, max=300),
io.Float.Input("duration", default=120.0, min=0.0, max=2000.0, step=0.1),
io.Combo.Input("timesignature", options=['2', '3', '4', '6']),
io.Combo.Input("language", options=["en", "ja", "zh", "es", "de", "fr", "pt", "ru", "it", "nl", "pl", "tr", "vi", "cs", "fa", "id", "ko", "uk", "hu", "ar", "sv", "ro", "el"]),
io.Combo.Input("keyscale", options=[f"{root} {quality}" for quality in ["major", "minor"] for root in ["C", "C#", "Db", "D", "D#", "Eb", "E", "F", "F#", "Gb", "G", "G#", "Ab", "A", "A#", "Bb", "B"]]),
io.Boolean.Input("generate_audio_codes", default=True, tooltip="Enable the LLM that generates audio codes. This can be slow but will increase the quality of the generated audio. Turn this off if you are giving the model an audio reference.", advanced=True),
io.Float.Input("cfg_scale", default=2.0, min=0.0, max=100.0, step=0.1, advanced=True),
io.Float.Input("temperature", default=0.85, min=0.0, max=2.0, step=0.01, advanced=True),
io.Float.Input("top_p", default=0.9, min=0.0, max=2000.0, step=0.01, advanced=True),
io.Float.Input(
"duration", default=120.0, min=0.0, max=2000.0, step=0.1
),
io.Combo.Input("timesignature", options=["2", "3", "4", "6"]),
io.Combo.Input(
"language",
options=[
"ar",
"az",
"bg",
"bn",
"ca",
"cs",
"da",
"de",
"el",
"en",
"es",
"fa",
"fi",
"fr",
"he",
"hi",
"hr",
"ht",
"hu",
"id",
"is",
"it",
"ja",
"ko",
"la",
"lt",
"ms",
"ne",
"nl",
"no",
"pa",
"pl",
"pt",
"ro",
"ru",
"sa",
"sk",
"sr",
"sv",
"sw",
"ta",
"te",
"th",
"tl",
"tr",
"uk",
"ur",
"vi",
"yue",
"zh",
"unknown",
],
),
io.Combo.Input(
"keyscale",
options=[
f"{root} {quality}"
for quality in ["major", "minor"]
for root in [
"C",
"C#",
"Db",
"D",
"D#",
"Eb",
"E",
"F",
"F#",
"Gb",
"G",
"G#",
"Ab",
"A",
"A#",
"Bb",
"B",
]
],
),
io.Boolean.Input(
"generate_audio_codes",
default=True,
tooltip="Enable the LLM that generates audio codes. This can be slow but will increase the quality of the generated audio. Turn this off if you are giving the model an audio reference.",
advanced=True,
),
io.Float.Input(
"cfg_scale",
default=2.0,
min=0.0,
max=100.0,
step=0.1,
advanced=True,
),
io.Float.Input(
"temperature",
default=0.85,
min=0.0,
max=2.0,
step=0.01,
advanced=True,
),
io.Float.Input(
"top_p", default=0.9, min=0.0, max=2000.0, step=0.01, advanced=True
),
io.Int.Input("top_k", default=0, min=0, max=100, advanced=True),
io.Float.Input("min_p", default=0.000, min=0.0, max=1.0, step=0.001, advanced=True),
io.Float.Input(
"min_p", default=0.000, min=0.0, max=1.0, step=0.001, advanced=True
),
],
outputs=[io.Conditioning.Output()],
)
@classmethod
def execute(cls, clip, tags, lyrics, seed, bpm, duration, timesignature, language, keyscale, generate_audio_codes, cfg_scale, temperature, top_p, top_k, min_p) -> io.NodeOutput:
tokens = clip.tokenize(tags, lyrics=lyrics, bpm=bpm, duration=duration, timesignature=int(timesignature), language=language, keyscale=keyscale, seed=seed, generate_audio_codes=generate_audio_codes, cfg_scale=cfg_scale, temperature=temperature, top_p=top_p, top_k=top_k, min_p=min_p)
def execute(
cls,
clip,
tags,
lyrics,
seed,
bpm,
duration,
timesignature,
language,
keyscale,
generate_audio_codes,
cfg_scale,
temperature,
top_p,
top_k,
min_p,
) -> io.NodeOutput:
tokens = clip.tokenize(
tags,
lyrics=lyrics,
bpm=bpm,
duration=duration,
timesignature=int(timesignature),
language=language,
keyscale=keyscale,
seed=seed,
generate_audio_codes=generate_audio_codes,
cfg_scale=cfg_scale,
temperature=temperature,
top_p=top_p,
top_k=top_k,
min_p=min_p,
)
conditioning = clip.encode_from_tokens_scheduled(tokens)
return io.NodeOutput(conditioning)
@ -71,7 +219,11 @@ class EmptyAceStepLatentAudio(io.ComfyNode):
inputs=[
io.Float.Input("seconds", default=120.0, min=1.0, max=1000.0, step=0.1),
io.Int.Input(
"batch_size", default=1, min=1, max=4096, tooltip="The number of latent images in the batch."
"batch_size",
default=1,
min=1,
max=4096,
tooltip="The number of latent images in the batch.",
),
],
outputs=[io.Latent.Output()],
@ -80,7 +232,10 @@ class EmptyAceStepLatentAudio(io.ComfyNode):
@classmethod
def execute(cls, seconds, batch_size) -> io.NodeOutput:
length = int(seconds * 44100 / 512 / 8)
latent = torch.zeros([batch_size, 8, 16, length], device=comfy.model_management.intermediate_device())
latent = torch.zeros(
[batch_size, 8, 16, length],
device=comfy.model_management.intermediate_device(),
)
return io.NodeOutput({"samples": latent, "type": "audio"})
@ -92,9 +247,15 @@ class EmptyAceStep15LatentAudio(io.ComfyNode):
display_name="Empty Ace Step 1.5 Latent Audio",
category="latent/audio",
inputs=[
io.Float.Input("seconds", default=120.0, min=1.0, max=1000.0, step=0.01),
io.Float.Input(
"seconds", default=120.0, min=1.0, max=1000.0, step=0.01
),
io.Int.Input(
"batch_size", default=1, min=1, max=4096, tooltip="The number of latent images in the batch."
"batch_size",
default=1,
min=1,
max=4096,
tooltip="The number of latent images in the batch.",
),
],
outputs=[io.Latent.Output()],
@ -103,9 +264,13 @@ class EmptyAceStep15LatentAudio(io.ComfyNode):
@classmethod
def execute(cls, seconds, batch_size) -> io.NodeOutput:
length = round((seconds * 48000 / 1920))
latent = torch.zeros([batch_size, 64, length], device=comfy.model_management.intermediate_device())
latent = torch.zeros(
[batch_size, 64, length],
device=comfy.model_management.intermediate_device(),
)
return io.NodeOutput({"samples": latent, "type": "audio"})
class ReferenceAudio(io.ComfyNode):
@classmethod
def define_schema(cls):
@ -121,15 +286,20 @@ class ReferenceAudio(io.ComfyNode):
],
outputs=[
io.Conditioning.Output(),
]
],
)
@classmethod
def execute(cls, conditioning, latent=None) -> io.NodeOutput:
if latent is not None:
conditioning = node_helpers.conditioning_set_values(conditioning, {"reference_audio_timbre_latents": [latent["samples"]]}, append=True)
conditioning = node_helpers.conditioning_set_values(
conditioning,
{"reference_audio_timbre_latents": [latent["samples"]]},
append=True,
)
return io.NodeOutput(conditioning)
class AceExtension(ComfyExtension):
@override
async def get_node_list(self) -> list[type[io.ComfyNode]]:
@ -141,5 +311,6 @@ class AceExtension(ComfyExtension):
ReferenceAudio,
]
async def comfy_entrypoint() -> AceExtension:
return AceExtension()