This ComfyUI workflow focuses on comparing the ACE-Step 1.5 Music Generation model with its smaller variants. The primary objective is to evaluate the enhanced audio understanding and composition capabilities of the 4B model version. By using a text prompt to generate music, users can explore the differences in audio quality, complexity, and fidelity between the models. The workflow employs various nodes such as KSampler, VAEDecodeAudio, and TextEncodeAceStepAudio1.5 to facilitate this comparison. Key differences include the model's ability to handle more intricate compositions and produce richer audio textures, which are particularly noticeable when generating longer or more complex musical pieces.
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 1.5 Music Generation (4B LLM )" (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_5_split_4b_api.json");
const job = await client.run(wf);
await job.getOutputs("107")[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
