9Graph nodes
9Node classes
16Inputs
1Models
Tags: 2026-sotaace-step-1.5audiocinematiccuemusicscore
Inputs (16)#
The typed parameter surface callers bind when they request this workflow. Enum options and numeric bounds are the values the workflow document declares.
promptstringrequiredDescribe the musical cue intent
cue_purposeenumdefault character_themeNarrative purpose of the cue
options:
build_tensioncharacter_themechasetransitionvictoryambient_loopmoodenumdefault heroicEmotional mood
options:
upliftingmysterioussomberheroicaggressivecalminstrumentationenumdefault hybrid_orchestralPrimary instrument family
options:
hybrid_orchestralsynthwaveambient_texturespercussion_focusacoustic_ensembletempo_bpmintegerdefault 96min 60max 180Target tempo in BPM
duration_secondsintegerdefault 20min 8max 90Cue duration in seconds
audio_prompt_hintstringdefault Optional prompt-side conditioning hint applied when provider supports advanced audio conditioning
reference_audio_urlstringdefault Primary reference audio URL for melody/style conditioning when supported by backend
reference_audio_urlsarraydefault []Optional ordered list of additional reference audio URLs for conditioning stacks
style_reference_idstringdefault Optional provider-side style reference identifier
conditioning_strengthfloatdefault 0.65min 0max 2Conditioning strength for reference-audio guidance
conditioning_modeenumdefault autoAudio conditioning mode preference
options:
autoreference-audiomelodystyle-transfervoice-cloneprovider_capability_modeenumdefault autoHow strictly provider support for reference-audio conditioning is enforced
options:
autorequireddisabledseedintegerdefault -1Random seed
lyricsstringdefault [inst]Lyrics; [inst] for instrumental
keyscalestringdefault E minorKey/scale, e.g. "E minor" or "C major" (invalid values fail loudly at the node)
ComfyUI node graph (9)#
The executable ComfyUI prompt graph: 9 nodes across 9 distinct node classes, wired by 11 data dependencies. Nodes tinted green come from a custom node pack this workflow declares; the rest are ComfyUI core / baked-community classes.
flowchart TD
n0["1: CheckpointLoaderSimple"]
n1["2: TextEncodeAceStepAudio1.5"]
n2["3: ConditioningZeroOut"]
n3["4: EmptyAceStep1.5LatentAudio"]
n4["5: ModelSamplingAuraFlow"]
n5["6: KSampler"]
n6["7: VAEDecodeAudio"]
n7["8: AudioLimiter"]
n8["9: SaveAudioMP3"]
n0 -->|clip| n1
n1 -->|conditioning| n2
n0 -->|model| n4
n4 -->|model| n5
n1 -->|positive| n5
n2 -->|negative| n5
n3 -->|latent_image| n5
n5 -->|samples| n6
n0 -->|vae| n6
n6 -->|audio| n7
n7 -->|audio| n8
classDef custom fill:#12b886,stroke:#0b6b4f,color:#04110c;
class n7 custom;
Nodes (9)#
1CheckpointLoaderSimplecoreckpt_name = ace_step_1.5_turbo_aio.safetensorsoutputs:
MODELCLIPVAE2TextEncodeAceStepAudio1.5coreclip = ◂ node 1 · out[1]tags = {{constructed_prompt}} tmpllyrics = {{lyrics}} tmplseed = {{seed}} tmplbpm = {{tempo_bpm}} tmplduration = {{duration_seconds}} tmpltimesignature = 4language = enkeyscale = {{keyscale}} tmploutputs:
CONDITIONING3ConditioningZeroOutcoreconditioning = ◂ node 2 · out[0]outputs:
CONDITIONING4EmptyAceStep1.5LatentAudiocoreseconds = {{duration_seconds}} tmplbatch_size = 1outputs:
LATENT5ModelSamplingAuraFlowcoremodel = ◂ node 1 · out[0]shift = 3.0outputs:
MODEL6KSamplercoremodel = ◂ node 5 · out[0]positive = ◂ node 2 · out[0]negative = ◂ node 3 · out[0]latent_image = ◂ node 4 · out[0]seed = {{seed}} tmplsteps = 8cfg = 1.0sampler_name = eulerscheduler = simpledenoise = 1.0outputs:
LATENT7VAEDecodeAudiocoresamples = ◂ node 6 · out[0]vae = ◂ node 1 · out[2]outputs:
AUDIO8AudioLimitercustom packaudio = ◂ node 7 · out[0]ceiling_db = -1.0outputs:
AUDIO9SaveAudioMP3coreaudio = ◂ node 8 · out[0]filename_prefix = music_cue_composerquality = V0Prompt construction#
template{prompt}, cue purpose: {cue_purpose}, mood: {mood}, instrumentation: {instrumentation}, {tempo_bpm} BPMVariables (5)#
prompt{{prompt}} tmplcue_purpose{{cue_purpose}} tmplmood{{mood}} tmplinstrumentation{{instrumentation}} tmpltempo_bpm{{tempo_bpm}} tmplModels & dependencies#
Custom node packs (1)#
The non-core ComfyUI node classes this graph requires; the RunPod worker image the workflow runs on must bake or install a pack that provides every one of them.
AudioLimiterModels required (1)#
ace_step_1.5_turbo_aio.safetensorsOutput contract#
What a successful run of this workflow returns.
typeaudioformatmp3codecpcm_s16lechannels2descriptionMusic cue master renderaudio_package{"mixdown": {"artifact_id": "audio_mixdown", "path_template": "audio/{{job_id}}/mixdown/music-master.wav", "format": "wav", "sample_rate_hz": 48000, "bit_depth": 24, "channels": 2, "codec": "pcm_s24le"}, "stems": {"format": "wav", "sample_rate_hz": 48000, "bit_depth": 24, "channels": 2, "artifacts": [{"stem": "drums", "artifact_id": "stem_drums", "path_template": "audio/{{job_id}}/stems/drums.wav", "required": false}, {"stem": "bass", "artifact_id": "stem_bass", "path_template": "audio/{{job_id}}/stems/bass.wav", "required": false}, {"stem": "lead", "artifact_id": "stem_lead", "path_template": "audio/{{job_id}}/stems/lead.wav", "required": true}, {"stem": "other", "artifact_id": "stem_other", "path_template": "audio/{{job_id}}/stems/other.wav", "required": false}], "archive": {"artifact_id": "stems_archive", "path_template": "audio/{{job_id}}/stems/stems.zip", "format": "zip"}}, "multi_track": {"format": "wav", "sample_rate_hz": 48000, "bit_depth": 24, "channels": 2, "artifacts": [{"track": "dialogue", "artifact_id": "multitrack_dialogue", "path_template": "audio/{{job_id}}/multitrack/dialogue.wav", "required": false}, {"track": "sfx", "artifact_id": "multitrack_sfx", "path_template": "audio/{{job_id}}/multitrack/sfx.wav", "required": false}, {"track": "music", "artifact_id": "multitrack_music", "path_template": "audio/{{job_id}}/multitrack/music.wav", "required": true}], "archive": {"artifact_id": "multitrack_archive", "path_template": "audio/{{job_id}}/multitrack/multitrack.zip", "format": "zip"}}, "loudness": {"artifact_id": "loudness_report", "path_template": "audio/{{job_id}}/analysis/loudness-report.json", "format": "json", "standard": "spotify", "target_integrated_lufs": -14, "max_true_peak_dbtp": -1}, "compliance": {"artifact_id": "audio_compliance_report", "path_template": "audio/{{job_id}}/analysis/audio-compliance-report.json", "format": "json", "loudness_tolerance_lufs": 1.0, "true_peak_tolerance_dbtp": 0.3, "max_clipping_percent": 0.1, "enforce_format_normalization": true}, "cue_sheet": {"artifact_id": "cue_sheet", "path_template": "audio/{{job_id}}/metadata/cue-sheet.csv", "format": "csv", "include_timecode": true, "include_beat_markers": true, "include_sections": true}}Taxonomy & routing#
How the control plane classifies this workflow — from the committed workflow-taxonomy-registry.json. It drives the consistency / control surface the agentic director can exercise over the workflow.
assetFamilysocial-audio-hook-loop-packoutputPackageProfileaudio-master-profilecontrolModalitiescamera-lockcolor-script-lockdepth-constraintidentity-adapterlatent-reusemodel-lockpalette-lockpose-constraintprompt-template-lockreference-ensemblesampler-scheduler-lockscene-lockseed-lockstyle-anchorstyle-locktemporal-lock +1 moreconsistencyDimensionsmotioncolor-scriptnotesAuto-mapped from audio defaults