ComfyUI Node
ACE-Step v1.5 Base
A ComfyUI node in Runware/Audio/runware with 25 inputs and 1 output.
ACE-Step v1.5 Base
- audioSettings
- audio
◄positivePrompt—►
◄audio►
◄negativePrompt►
◄seed0►
◄steps100►
◄CFGScale10.00►
◄strengthfalse►
◄strength_value0.50►
◄duration60.0►
◄numberResults1►
◄settings.bpmfalse►
◄settings.bpm_value30►
◄settings.guidanceTypeapg►
◄settings.keyScale►
◄settings.lyrics►
◄settings.repaintingStartfalse►
◄settings.repaintingStart_value-300.00►
◄settings.repaintingEndfalse►
◄settings.repaintingEnd_value0.00►
◄settings.timeSignature(default)►
◄settings.vocalLanguageen►
◄ttlfalse►
◄ttl_value60►
◄outputFormatMP3►
CategoryRunware/Audio/runware
Inputs (25)
| Name | Type | Default | Description |
|---|---|---|---|
| positivePrompt | STRING | Text prompt describing elements to include in the generated output. | |
| audioSettingsopt | RUNWARE_AUDIOSETTINGS | — | |
| audioopt | STRING | Audio input (UUID or URL). | |
| negativePromptopt | STRING | Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1). | |
| seedopt | INT | 00–2147483647 | Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range. |
| stepsopt | INT | 1001–300 | Total number of denoising steps. Higher values generally produce more detailed results but take longer. |
| CFGScaleopt | FLOAT | 10.001–30 | Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt. |
| strengthopt | BOOLEAN | false | Enable to set strength. This setting has usage rules in this model, so it is off unless you enable it. |
| strength_valueopt | FLOAT | 0.500–1 | Fraction of steps using the input source instead of generated output. |
| durationopt | FLOAT | 60.030–300 | Length of the generated audio track in seconds. |
| numberResultsopt | INT | 11–4 | Number of results to generate. Each result uses a different seed, producing variations of the same parameters. |
| settings.bpmopt | BOOLEAN | false | Enable to set settings.bpm. Off uses the model's default. |
| settings.bpm_valueopt | INT | 3030–300 | Beats per minute. If not set, the model decides automatically. |
| settings.guidanceTypeopt | COMBO | apg | Controls how guidance is applied during generation. |
| settings.keyScaleopt | STRING | Musical key and scale in '{Note}{Accidental} {Mode}' format (e.g. 'C major', 'F# minor', 'Bb major'). | |
| settings.lyricsopt | STRING | Song lyrics, typically formatted like a lyrics website. | |
| settings.repaintingStartopt | BOOLEAN | false | Enable to set settings.repaintingStart. Off uses the model's default. |
| settings.repaintingStart_valueopt | FLOAT | -300.00-300–300 | Start time in seconds for repaint region. Requires input audio. Negative values prepend audio before the start. |
| settings.repaintingEndopt | BOOLEAN | false | Enable to set settings.repaintingEnd. Off uses the model's default. |
| settings.repaintingEnd_valueopt | FLOAT | 0.000–300 | End time in seconds for repaint region. Requires input audio. Values beyond audio duration append new audio. |
| settings.timeSignatureopt | COMBO | (default) | Beats per measure. If not set, the model decides automatically. |
| settings.vocalLanguageopt | COMBO | en | ISO 639-1 language code for vocals. `unknown` for instrumental or auto detection. |
| ttlopt | BOOLEAN | false | Enable to set ttl. Off uses the model's default. |
| ttl_valueopt | INT | 60 | Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`. |
| outputFormatopt | COMBO | MP3 | File format for the generated audio. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |