ACE-Step 1.5 by Comfy-Org

ACE-Step 1.5 by Comfy-Org

Model files for generating music from text in ComfyUI, repackaged from the original ACE-Step 1.5 release. Includes checkpoint, diffusion, text encoder and VAE files and a set of ready workflows.

Made by Comfy-Org on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: These are the ACE-Step 1.5 model files repackaged to work in ComfyUI, so you can generate music from a text description. The repository holds a checkpoint, several diffusion models, three text encoders and a VAE. The card also lists ComfyUI workflows that use them. The original model lives in the ACE-Step repository.

Who it suits: It suits ComfyUI users who want a text-to-music setup without assembling the files themselves, and anyone who wants to try ACE-Step 1.5 in a node-based tool.

Industry | Who uses it | How they use it | Example
Music and audio | Hobby musicians | Draft a song from a text description | A music clip comes back from a written prompt
Video and content | Creators who need background music | Generate a track for a project | They preview the card's audio samples before choosing a workflow
Songwriting | People who work with lyrics | Use the AI Lyric Song Generation workflow | A song is built around the lyrics they supply

You can skip it if you do not use ComfyUI, since these files are packaged for it.

Where to use it:

• ComfyUI, on Windows, macOS or Linux
• ComfyUI workflow templates from Comfy-Org that are named for ACE-Step 1.5
• Python with the Hugging Face tools, to download the files

Use case | Who | What they get back
Text to music | Creators | A music clip generated from a text prompt
Song generation with lyrics | Songwriters | A song generated from lyrics through the lyric workflow
Trying different model variants | ComfyUI users | Turbo, base and XL runs to compare

How to set it up: You need ComfyUI and a place for each downloaded file.

• A working ComfyUI install
• Python with the huggingface_hub package
• Disk space for the checkpoint, diffusion models, text encoders and VAE

1. Install the Hugging Face tools with Python.
2. Download the repository files with the second command below.
3. Place each file in the matching folder under ComfyUI/models, as the table below shows.
4. Open one of the listed workflows in ComfyUI.

pip install -U huggingface_hub
hf download Comfy-Org/ACE-Step-1.5

Title: Where each file goes under ComfyUI/models
Folder | File
checkpoints | ace_step_1.5_turbo_aio.safetensors
diffusion_models | acestep_v1.5_base.safetensors
diffusion_models | acestep_v1.5_turbo.safetensors
diffusion_models | acestep_v1.5_xl_base_bf16.safetensors
diffusion_models | acestep_v1.5_xl_sft_bf16.safetensors
diffusion_models | acestep_v1.5_xl_turbo_bf16.safetensors
text_encoders | qwen_0.6b_ace15.safetensors
text_encoders | qwen_1.7b_ace15.safetensors
text_encoders | qwen_4b_ace15.safetensors
vae | ace_1.5_vae.safetensors

How to use it: The card gives no command. Open one of the listed workflows in ComfyUI, describe the music you want, and run it. Some workflows have audio previews on the card, so you can hear sample output first.

Tool | What it does
XL Turbo, Text to Music | Workflow for text-to-music with the XL turbo model
XL SFT, Text to Music | Workflow for text-to-music with the XL SFT model
XL Base, Text to Music | Workflow for text-to-music with the XL base model
ACE-Step 1.5 Music Generation AIO | Music workflow that matches the all-in-one checkpoint
ACE-Step 1.5 Music Generation Workflow | Music workflow that uses the separate model files
AI Lyric Song Generation | Workflow for songs built around lyrics

Example: You place the files, open the ACE-Step 1.5XL Turbo workflow, type a description of the song you want, and run it. ComfyUI returns a generated music clip as audio, much like the previews on the card.

For newcomers and experts: Think of it as a music generator that lives inside ComfyUI. A first small try is to put the files in their folders, open a workflow from the list and run it with a short description.

The repository splits the model into parts that ComfyUI loads separately. Diffusion models come in base, turbo and SFT variants, with XL versions in bf16. Three text encoders of different sizes sit beside a single VAE. An all-in-one checkpoint for the turbo model bundles the pieces for a simpler setup.

Place the files in the ComfyUI models folders
Open an ACE-Step 1.5 workflow in ComfyUI
Write a text prompt for the music
Run the workflow
Get a generated music clip

Good to know:

• Repackaged files: they are the original ACE-Step 1.5 weights arranged for ComfyUI, and the original model repository is the ACE-Step one
• Folders matter: each file belongs in its own subfolder under ComfyUI/models
• Variants: several diffusion models and three text encoder sizes are included, so you do not need all of them for one workflow
• License: Apache 2.0
• Cost to run: none named
• Data it reaches: the files you download and the prompts you run in ComfyUI
• Not for: use outside ComfyUI, since the files are repackaged for it

On Hugging Face, 13 November 2026

• Task: text to audio
• Library: diffusion-single-file
• Downloads in the last 30 days: 815,468
• Likes: 187
• License: apache-2.0
• Based on: ACE-Step/Ace-Step1.5
• Tags: diffusion-single-file, comfyui, text-to-audio

Links

• Model: https://huggingface.co/Comfy-Org/ACE-Step-1.5
• Files: https://huggingface.co/Comfy-Org/ACE-Step-1.5/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download Comfy-Org/ACE-Step-1.5

Then follow the usage in its model card. Nothing in this kit runs by itself.