ACE-Step

ACE-Step

Application Docker from SpaceInvaderOne's Repository

Vue d'ensemble

ACE-Step 1.5 - AI Music Generation. Generate full songs with vocals, instrumentals, and lyrics using a Diffusion Transformer. Supports text-to-music, remixing, cover generation, and LoRA fine-tuning. Requires NVIDIA GPU with CUDA support.

FIRST RUN: Models (~10GB) will be downloaded automatically on first start. This may take several minutes depending on your internet speed. Subsequent starts are instant.

SETTINGS GUIDE:

DiT Model - The core music generation model.

  • turbo (default): Fast generation in 8 steps. Best for most users.
  • turbo-rl: Turbo with reinforcement learning refinement.
  • sft: Higher quality, 50 steps (slower).
  • base: 50 steps with all features (extract, lego, complete).

Language Model - Controls lyrics understanding and chain-of-thought reasoning.

  • 1.7B (default): Best balance of quality and VRAM. Recommended for 12-16GB GPUs.
  • 0.6B: For GPUs with less than 12GB VRAM.
  • 4B: Highest quality lyrics understanding. Requires 24GB+ VRAM.

Enable LLM - Whether to load the language model.

  • auto (default): Detects based on your GPU VRAM.
  • false: DiT-only mode. Faster startup, uses less VRAM, but disables thinking/sample features.
  • true: Force enable.

LM Backend - Engine for the language model.

  • pt (default): PyTorch native. Works on all GPUs including RTX 50-series.
  • vllm: Faster inference but may crash on RTX 50-series (Blackwell) GPUs.

CPU Offloading - Moves models between GPU and CPU to save VRAM.

  • auto (default): Offloads if GPU has less than 20GB VRAM.
  • false: Keep all models on GPU. Faster generation but uses ~12GB VRAM at idle.
  • true: Always offload. Slower but frees VRAM for other containers.

UI Language - Web interface language: English, Chinese, or Japanese.

Exigences

IMPORTANT: This image requires at least 20GB of free space in your Docker vDisk. Check Settings > Docker > Docker vDisk Size and increase if needed. Requires NVIDIA GPU with 8GB+ VRAM (12GB+ recommended for full features). Models (~10GB) are downloaded on first run to the mapped checkpoints volume.

Arguments d'exécution

Interface utilisateur Web
http://[IP]:[PORT:7860]/
Réseau
bridge
Coquille
bash
Privilégié
false
Paramètres supplémentaires
--gpus all --user root

Configuration du modèle

Web UI PortPorttcp

Gradio Web UI and REST API port

Cible
7860
Défaut
7860
Valeur
7860
Model CheckpointsPathrw

AI model files (~10GB, auto-downloaded on first run)

Cible
/app/checkpoints
Défaut
/mnt/user/appdata/ace-step/checkpoints
Valeur
/mnt/user/appdata/ace-step/checkpoints
Generated MusicPathrw

Generated music files output directory

Cible
/app/gradio_outputs
Défaut
/mnt/user/appdata/ace-step/output
Valeur
/mnt/user/appdata/ace-step/output
DiT ModelVariable{3}

Diffusion model variant. Turbo=8 steps (fast), SFT=50 steps (quality), Base=50 steps (all features including extract/lego/complete).

Cible
ACESTEP_CONFIG_PATH
Défaut
acestep-v15-turbo|acestep-v15-turbo-rl|acestep-v15-sft|acestep-v15-base
Valeur
acestep-v15-turbo
Language ModelVariable{3}

Chain-of-thought LM size. 1.7B recommended for 16GB VRAM. 4B needs 24GB+. 0.6B for low VRAM.

Cible
ACESTEP_LM_MODEL_PATH
Défaut
acestep-5Hz-lm-1.7B|acestep-5Hz-lm-0.6B|acestep-5Hz-lm-4B
Valeur
acestep-5Hz-lm-1.7B
Enable LLMVariable{3}

Auto detects based on GPU VRAM. Set false for DiT-only mode (faster, no thinking/sample features).

Cible
ACESTEP_INIT_LLM
Défaut
auto|true|false
Valeur
auto
LM BackendVariable{3}

pt (PyTorch native) is recommended for RTX 50-series. vllm (nano-vllm) is faster but may segfault on Blackwell GPUs.

Cible
ACESTEP_LM_BACKEND
Défaut
pt|vllm
Valeur
pt
UI LanguageVariable{3}

Web interface language

Cible
LANGUAGE
Défaut
en|zh|ja
Valeur
en
CPU OffloadingVariable{3}

auto = ACE-Step decides based on VRAM (offloads below 20GB). false = keep all models on GPU (faster, needs ~12GB idle VRAM). true = offload models to CPU between steps (slower, saves VRAM for shared GPU use).

Cible
ACESTEP_OFFLOAD_CPU
Défaut
auto|false|true
Valeur
auto
Web UI Port (internal)Variable{3}

Internal port for Gradio server (should match the port mapping above)

Cible
PORT
Défaut
7860
Valeur
7860
Batch SizeVariable{3}

Default generation batch size (1-8). Leave empty for auto (min(2, GPU max)).

Cible
ACESTEP_BATCH_SIZE
CUDA Visible DevicesVariable{3}

Which GPU(s) to use. 0 = first GPU.

Cible
CUDA_VISIBLE_DEVICES
Défaut
0
Valeur
0
Download SourceVariable{3}

Model download source. Auto tries HuggingFace first, falls back to ModelScope.

Cible
ACESTEP_DOWNLOAD_SOURCE
Défaut
auto|huggingface|modelscope
Valeur
auto

Télécharger les statistiques

2,023
Total des téléchargements

Détails

Référentiel
spaceinvaderone/ace-step:latest
Dernière mise à jour2026-02-22
Première vue2026-02-22

Exécutez ACE-Step sur Unraid.

ACE-Step est listé dans Community Apps pour Unraid OS. Explorez Unraid pour créer un serveur domestique flexible, un NAS ou un laboratoire domestique.