Skip to main content

ComfyUI Workflow · AI Music · Free · 2026

ACE-Step 1.5: The Best Free Suno AI Alternative for ComfyUI

Generate high-quality AI music for free on your own PC using ACE-Step 1.5 in ComfyUI. Supports Pop, Rock, Hip-Hop, EDM, Jazz, Country, Metal, and 50+ languages.

By Earngenix TeamUpdated 202612 min read

ACE-Step 1.5: Free AI Music Generation in ComfyUI

Quick answer: ACE-Step 1.5 is a free, open-source AI music generation model that runs locally in ComfyUI. It is a genuine free alternative to Suno AI — no subscription, no usage limits, and you keep full control of your generated music.

Looking for a free way to generate music like Suno AI? ACE-Step 1.5 is an open-source model you can run entirely on your own computer through ComfyUI. It supports many music styles, allows you to control lyrics, BPM, key scale, and song length, and works well on regular gaming PCs.

What Is ACE-Step 1.5?

ACE-Step 1.5 is an open-source AI music generation model. It lets you create full songs in different genres, control musical style through captions and lyrics, edit parts of existing songs, and even convert vocals into background music. It supports over 50 languages for lyrics and runs locally without any cloud dependency.

Completely Free

Open-source with no usage limits or subscription fees.

Multiple Genres

Pop, Rock, Hip-Hop, EDM, Jazz, Country, Metal, and more.

50+ Languages

Write lyrics in English, Spanish, Japanese, and many others.

Runs Locally

No internet required after setup. Runs on your own GPU.

Music Genres Supported — Listen & Download Workflows

Listen to sample tracks generated with ACE-Step 1.5 in ComfyUI. Each genre has a dedicated workflow you can download and use immediately. The caption and lyrics used for each track are included inside the workflow JSON file.

Pop

Download Pop Workflow

The caption and lyrics used for this track are included in the workflow JSON file.

Rock

Download Rock Workflow

The caption and lyrics used for this track are included in the workflow JSON file.

Hip-Hop

Download Hip-Hop Workflow

The caption and lyrics used for this track are included in the workflow JSON file.

Electronic Dance Music (EDM)

Download Electronic Dance Music (EDM) Workflow

The caption and lyrics used for this track are included in the workflow JSON file.

Country

Download Country Workflow

The caption and lyrics used for this track are included in the workflow JSON file.

Jazz

Download Jazz Workflow

The caption and lyrics used for this track are included in the workflow JSON file.

Metal

Download Metal Workflow

The caption and lyrics used for this track are included in the workflow JSON file.

How to Use ACE-Step 1.5 with ComfyUI

Step 1 — Update ComfyUI

Before loading the ACE-Step workflow, make sure your ComfyUI is fully up to date.

1Switch to the latest ComfyUI version

Open the ComfyUI Manager, click Switch ComfyUI, and select the latest version available.

ComfyUI Manager showing the Switch ComfyUI option for updating to the latest version — Open ComfyUI Manager and switch to the latest version.

2Update all nodes and extensions

Click Update All in the Manager to upgrade all custom nodes and extensions.

ComfyUI Manager showing the Update All button to upgrade all nodes and extensions — Click Update All to ensure all nodes are on the latest version.

💡 Tip: Always update before loading a new workflow — outdated nodes cause the most common errors.

Step 2 — Fix Common Issues After Update

No Module Named 'comfyui_aimdo' Error

If you see this error after updating ComfyUI, you need to install the missing package manually:

No Module named 'comfyui_aimdo'

Open your comfyui_windows_portable folder (where ComfyUI and python_embeded are located).
Click in the folder address bar, type cmd, and press Enter to open a terminal in that folder.
Run the command below:

ComfyUI Windows portable folder showing ComfyUI and python_embeded subfolders — Open your comfyui_windows_portable folder and open a terminal here.

.\python_embeded\python.exe -m pip install comfy-aimdo

Windows command prompt showing the pip install comfy-aimdo command running successfully in the ComfyUI portable folder — Run this command to install the missing comfy-aimdo package.

Check the Run Command (Windows)

If ACE-Step 1.5 generation is extremely slow or stuck, check your run_nvidia_gpu.bat file. Right-click it and choose Edit.

Make sure it contains exactly this command — do NOT include --lowvram:

.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build

⚠️ Warning: The --lowvram flag makes ACE-Step 1.5 music generation extremely slow — sometimes taking hours instead of minutes. Remove it if it is present.

run_nvidia_gpu.bat file opened in Notepad showing the correct launch command without --lowvram flag — Your run_nvidia_gpu.bat should look like this — no --lowvram flag.

Step 3 — Download the ACE-Step 1.5 Workflow

Download the main ACE-Step 1.5 ComfyUI workflow below. Drag and drop the JSON file into ComfyUI to load it.

Download ACE-Step 1.5 ComfyUI Workflow

Model Files You Need

Download all four model files from Hugging Face and place them in the correct ComfyUI subfolders:

Diffusion Model

Diffusionacestep_v1.5_turbo.safetensors

Text Encoders

Text Encoder 1qwen_0.6b_ace15.safetensors

Text Encoder 2qwen_1.7b_ace15.safetensors

VAE

VAEace_1.5_vae.safetensors

Where to Put the Model Files

Place each file in the correct ComfyUI subfolder as shown below:

ComfyUI/
└── models/
    ├── diffusion_models/
    │   └── acestep_v1.5_turbo.safetensors
    ├── text_encoders/
    │   ├── qwen_0.6b_ace15.safetensors
    │   └── qwen_1.7b_ace15.safetensors
    └── vae/
        └── ace_1.5_vae.safetensors

💡 Tip: After placing the files, refresh your browser tab so ComfyUI detects the new models in the dropdowns.

Generating Your First Song

Once your workflow and models are ready, follow these steps to generate your first AI song:

1Set the Song Length

In the workflow, find the song length setting (measured in seconds) and choose how long you want the output to be.

ACE-Step 1.5 ComfyUI workflow showing the song length setting in seconds — Set the song duration in seconds in the workflow.

2Add a Caption

Type a short caption that describes the mood, genre, or idea of your song. The caption is the main style guide — be specific.

Example: "Upbeat pop song with female vocals, summer vibe, catchy chorus"

ACE-Step 1.5 workflow showing the caption text field where you describe the song style and mood — Add a caption describing your song's style and mood.

3Add Lyrics

Enter lyrics for the song. Lyrics help guide the melody, phrasing, and vocal style. You can write them in any of 50+ supported languages.

ACE-Step 1.5 workflow showing the lyrics input field with example song lyrics entered — Enter your lyrics — supports 50+ languages.

4Set BPM and Key Scale

Adjust the BPM (beats per minute) and key scale to match your intended musical style. If you are unsure what values to use, describe your song caption and lyrics to ChatGPT and ask for BPM and key suggestions.

ACE-Step 1.5 ComfyUI workflow showing the BPM and key scale settings for music generation — Set BPM and key scale to match your musical style.

5Run the Workflow

Click Run (or Queue Prompt) and wait for ACE-Step 1.5 to generate your song. Generation time depends on your GPU and the song length you set.

The output audio file will appear in ComfyUI when generation is complete. You can then save or export it from the output panel.

Tips and Troubleshooting

Do not use --lowvram in your run_nvidia_gpu.bat file.

Fix: The --lowvram flag makes music generation extremely slow with ACE-Step 1.5 — sometimes taking hours per song. Remove it from your .bat file and use the standard launch command.

Make sure all model files are in the correct subfolders.

Fix: If models are in the wrong folder, generation will fail or produce silence. Double-check the folder structure shown above: diffusion_models, text_encoders, and vae.

Getting errors after a ComfyUI update?

Fix: Open the Manager and click Install Missing Custom Nodes, then Update All. Make sure the comfy-aimdo package is installed using the pip command shown in this guide.

Output audio is silent or very short.

Fix: Check that the song length is set correctly (in seconds, not milliseconds). Also verify all three model types are loaded — diffusion, text encoders, and VAE are all required.

Frequently Asked Questions

ACE-Step 1.5 is a free, open-source AI music generation model that runs locally on your PC via ComfyUI. It supports over 50 languages and multiple genres including Pop, Rock, Hip-Hop, EDM, Jazz, Country, and Metal. It is a genuine free alternative to paid tools like Suno AI.

Yes. ACE-Step 1.5 is fully open-source and free to use. You run it locally on your own PC through ComfyUI, so there are no subscription fees, usage limits, or API costs.

ACE-Step 1.5 supports a wide range of genres including Pop, Rock, Hip-Hop, Electronic Dance Music (EDM), Jazz, Country, and Metal. Each genre has a dedicated ComfyUI workflow available for download in this guide.

The most common cause is the --lowvram flag in your run_nvidia_gpu.bat file. ACE-Step 1.5 is not compatible with --lowvram and it will make generation extremely slow. Remove that flag and run ComfyUI with the standard command: .\\python_embeded\\python.exe -s ComfyUI\\main.py --windows-standalone-build

This error appears after a ComfyUI update when the comfy-aimdo package is missing. Fix it by opening a terminal in your comfyui_windows_portable folder and running: .\\python_embeded\\python.exe -m pip install comfy-aimdo

Discussion

Join the discussion

Sign in to leave a comment or reply

💬

No comments yet

Be the first to share your thoughts!