Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > civitai-comfy-nodes > Civitai Ace Step Audio

ComfyUI Node: Civitai Ace Step Audio

Class Name

CivitaiAceStepAudio

Category
Civitai/Audio
Author
civitai (Account age: 1322days)
Extension
civitai-comfy-nodes
Latest Updated
2026-06-18
Github Stars
0.02K

How to Install civitai-comfy-nodes

Install this extension via the ComfyUI Manager by searching for civitai-comfy-nodes
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter civitai-comfy-nodes in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

Civitai Ace Step Audio Description

Node for creating and orchestrating audio content with advanced models and algorithms for high-quality output.

Civitai Ace Step Audio:

CivitaiAceStepAudio is a powerful node designed to facilitate the creation and orchestration of audio content using the aceStepAudio recipe from Civitai. This node is part of the Civitai/Audio category and is tailored to generate audio and video outputs based on a variety of input parameters. It leverages advanced models and algorithms to synthesize music and audio content, allowing you to specify details such as music description, lyrics, tempo, and more. The node's primary goal is to provide a seamless and efficient way to produce high-quality audio content, making it an invaluable tool for AI artists looking to explore creative audio generation.

Civitai Ace Step Audio Input Parameters:

music_description

This parameter allows you to provide a textual description of the music you wish to generate. It influences the overall theme and style of the audio output. There are no specific minimum or maximum values, but a well-crafted description can significantly enhance the quality of the generated audio.

lyrics

The lyrics parameter lets you input the words or phrases that you want to be included in the audio. This can be particularly useful for generating songs or spoken word content. Like music_description, there are no strict limits, but clarity and relevance to the desired output are important.

seed

The seed parameter is used to initialize the random number generator, ensuring reproducibility of the audio output. By setting a specific seed value, you can achieve consistent results across multiple runs. The default value is typically random, but you can specify any integer value.

duration

This parameter specifies the length of the audio in seconds. It directly impacts the duration of the generated audio content. The minimum value is 1 second, and the maximum can be set according to your needs, with a default value that suits typical use cases.

bpm

BPM, or beats per minute, determines the tempo of the music. It affects the speed and rhythm of the audio output. You can set this to any value that fits your musical vision, with common values ranging from 60 to 180 BPM.

time_signature

The time_signature parameter defines the musical time signature, which influences the rhythmic structure of the audio. Common values include 4/4, 3/4, and 6/8, but you can specify any valid time signature to match your creative intent.

language

This parameter allows you to specify the language of the lyrics or spoken content. It ensures that the generated audio aligns with the linguistic characteristics of the chosen language. Common options include English, Spanish, French, etc.

key

The key parameter sets the musical key for the audio, affecting the tonal center and harmony. You can choose from standard musical keys like C major, A minor, etc., to guide the melodic and harmonic content of the output.

instrumental_weight

This parameter controls the emphasis on instrumental elements in the audio. A higher value increases the prominence of instruments, while a lower value focuses more on vocals. The range is typically from 0 to 1, with a default balanced setting.

vocal_weight

Similar to instrumental_weight, this parameter adjusts the emphasis on vocal elements. It allows you to balance the mix between vocals and instruments, with values ranging from 0 to 1.

diffusion_model

The diffusion_model parameter specifies the model used for audio diffusion, impacting the style and quality of the output. You can select from available models, with "air" being a common default choice.

cover_json

This parameter allows you to input JSON data for cover art, which can be used to generate visual content alongside the audio. It enhances the multimedia aspect of the output.

clip_model

The clip_model parameter determines the model used for CLIP-based processing, influencing the semantic understanding of the input parameters. "air" is a typical default model.

vae_model

This parameter specifies the VAE (Variational Autoencoder) model used in the audio generation process, affecting the quality and characteristics of the output. "air" is a common default model.

language_model

The language_model parameter sets the model used for language processing, impacting the handling of lyrics and spoken content. "air" is a typical default choice.

steps

This parameter defines the number of processing steps in the audio generation pipeline. More steps can lead to higher quality but may increase processing time. The default value balances quality and efficiency.

cfg

The cfg parameter, or configuration, adjusts the overall settings for the audio generation process. It allows for fine-tuning of various aspects to achieve the desired output.

loras

This parameter allows you to input a map of LORA (Low-Rank Adaptation) strengths, which can be used to customize the audio generation process further. It provides additional control over the output characteristics.

Civitai Ace Step Audio Output Parameters:

blob_audio

This output provides the generated audio content in a binary blob format. It is the primary audio output of the node, containing the synthesized music or sound based on the input parameters.

blob_video

The blob_video output contains the generated video content, if applicable. It complements the audio output by providing visual elements that align with the audio theme.

workflow_id

This output provides a unique identifier for the workflow execution, allowing you to track and reference the specific audio generation process.

raw_json

The raw_json output contains the raw JSON data related to the audio generation process. It provides detailed information about the execution and can be used for debugging or analysis.

Civitai Ace Step Audio Usage Tips:

  • Experiment with different seed values to explore a variety of audio outputs while maintaining reproducibility.
  • Use detailed and descriptive inputs for music_description and lyrics to enhance the quality and relevance of the generated audio.

Civitai Ace Step Audio Common Errors and Solutions:

"Invalid seed value"

  • Explanation: The seed value provided is not a valid integer.
  • Solution: Ensure that the seed parameter is set to a valid integer value.

"Unsupported language"

  • Explanation: The specified language is not supported by the node.
  • Solution: Choose a language from the supported list, such as English, Spanish, or French.

"Duration exceeds maximum limit"

  • Explanation: The duration parameter is set to a value beyond the allowed maximum.
  • Solution: Adjust the duration to a value within the acceptable range, typically up to a few minutes.

Civitai Ace Step Audio Related Nodes

Go back to the extension to check out more related nodes.
civitai-comfy-nodes
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Civitai Ace Step Audio