The ACE Step v1 Text to Song workflow is a sophisticated process that transforms text prompts into fully realized songs with vocals. Utilizing the ACE-Step model, this workflow supports multilingual inputs and allows for extensive style customization, making it a versatile tool for audio content creators. At its core, the workflow employs several key nodes such as TextEncodeAceStepAudio for converting text into audio representations, and VAEDecodeAudio for decoding the latent audio into a final output. The workflow also includes nodes like LatentApplyOperationCFG and ModelSamplingSD3, which are crucial for refining the audio output by applying configuration and sampling techniques. This workflow is particularly useful for generating unique audio content, as it provides users with the ability to control various aspects of the song, including vocal volume and style, through nodes like ConditioningZeroOut and LatentOperationTonemapReinhard.
API
Use this workflow from code
Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.
Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.
// Install (beta)
npm i @comfyorg/sdk
// Run "ACE Step v1 Text to Song" (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
// This workflow, exported in API format (see note below)
const wf = await client.workflows.fromFile("audio_ace_step_1_t2a_song_api.json");
const job = await client.run(wf);
await job.getOutputs("59")[0].toFile("output.png"); // SaveAudioMP3The SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).
Comfy Cloud API access requires a plan with an API key.
FAQ
