Deploy ACE-Step 1.5 on Sealos

Open-source music generation AI. Commercial-grade quality, under 2s per song on A100. Supports text-to-music, cover generation, repainting, LoRA training, and 50+ languages.

Launch a private ACE-Step 1.5 AI workspace with one-click deployment.Keep models, prompts, and workflow data in your own Sealos environment.Scale GPU or CPU resources as your AI workload grows.Use an open-source template without managing Kubernetes YAML.

Official Website GitHub README

sealos.io

Why deploy on Sealos

Sealos makes deploying any app effortless, secure, and production-ready. From one-click launch to ongoing operations, we handle the heavy lifting so you can focus on what matters.

One-Click Deploy

Compute

Networking

Storage

Security

Observability

Your Application is Live

One-Click Deployment

Deploy any app template in seconds. No compose setup, manual configure, and go live.

Managed Kubernetes Reliability

Built on Sealos Managed Kubernetes for high availability, auto-scaling, and self-healing by default.

Automatic HTTPS & Security

Every deployment includes a secure domain with automatic SSL. We handle certificates and text protection for you.

Persistent Storage

Attach persistent volumes with ease. Your data stays safe, durable, and always accessible.

Scale when needed

Adjust resources as your app grows, no downtime required.

You Get the Whole Stack

Sealos provisions and connects every resource your application needs. Everything is ready to use.

One-click, fully provisionedSecure by defaultProduction ready

App Service

Your application is running and ready to serve requests.

Public HTTPS URL

Secure, global endpoint to access your application.

Database

Managed database instance for your application.

Persistent Volume

Durable storage for uploads and application data.

Environment Variables

Configuration and secrets injected securely into your app.

Logs & Metrics

Centralized logs and basic metrics are enabled.

README

README.md

ACE-Step 1.5

Overview

Open-source music generation AI. Commercial-grade quality, under 2s per song on A100. Supports text-to-music, cover generation, repainting, LoRA training, and 50+ languages.

This Sealos template deploys ACE-Step 1.5 as the ace-step application. It uses the repository-maintained Sealos manifest and keeps deployment, networking, and storage configuration inside the template.

Deploy on Sealos

Open this template in the Sealos App Store, review the configuration values, and click Deploy. Sealos renders the template variables, creates the required Kubernetes resources, and manages the public endpoint for the application.

Access

After deployment, open https://${{ defaults.app_host }}.${{ SEALOS_CLOUD_DOMAIN }}. The concrete hostname is generated from defaults.app_host and your Sealos Cloud domain.

Configuration

The following user-facing inputs are available during deployment:

Name	Description	Required	Default
`cpu_limit`	CPU limit (millicores, e.g. 4000 = 4 cores)	`false`	`4000`
`dit_model`	DiT model config: acestep-v15-turbo (fast) or acestep-v15 (quality)	`false`	`acestep-v15-turbo`
`gpu_count`	Number of GPUs (NVIDIA)	`true`	`1`
`init_service`	Auto-initialize models on startup (true/false). Set false to defer to UI button.	`false`	`true`
`llm_backend`	LLM backend: vllm (recommended for >=24GB VRAM) or pt (PyTorch, lower VRAM)	`false`	`pt`
`lm_model`	LM model: acestep-5Hz-lm-4B (best quality, >=24GB) / acestep-5Hz-lm-1.7B / acestep-5Hz-lm-0.6B (low VRAM)	`false`	`acestep-5Hz-lm-1.7B`
`memory_limit`	Memory limit (MiB)	`false`	`16384`
`output_volume_size`	Output storage size in GiB (generated audio files)	`false`	`10`
`startup_mode`	Startup mode: gradio (Web UI on port 7860) or api (REST API server on port 8001)	`true`	`gradio`
`volume_size`	Model storage size in GiB (checkpoints ~20GB)	`true`	`30`