ACE-Step 1.5XL Turbo: 텍스트를 음악으로

증류된 4B ACE-Step 모델을 사용하여 텍스트 프롬프트로 고품질 음악을 생성합니다. CFG 없이 단 8회의 추론 단계로 상업용 오디오를 생성합니다.

Input

Song lyrics with section tags like [Verse] and [Chorus]. Leave empty for an instrumental.

Genre, tempo, key, mood, instruments, arrangement and vocal style.

Length of the song.

Advanced settings

Tempo in beats per minute.

Default: 124

Musical key and scale.

Language the lyrics are sung in.

Leave empty for a new result each run. Enter a number to repeat one.

The turbo model is tuned for 8 steps.

Default: 8

Beats per bar (4 = 4/4).

Output
Example
00:00

예시 사용해 보기

이 워크플로 정보

This workflow turns a plain-language text prompt into finished music using the ACE-Step 1.5 XL Turbo model. Your prompt is encoded by TextEncodeAceStepAudio1.5 (backed by DualCLIPLoader) into audio-aware conditioning. EmptyAceStep1.5LatentAudio creates a blank latent audio canvas at your chosen length, and UNETLoader loads the distilled 4B ACE-Step checkpoint (acestep_v1.5_xl_turbo_bf16.safetensors). ModelSamplingAuraFlow configures the sampler schedule tuned for ACE-Step, and KSampler performs just 8 diffusion steps to synthesize the latent audio.

The audio is then reconstructed with VAELoader + VAEDecodeAudio and saved via SaveAudioMP3.

What makes this workflow practical is its “turbo” configuration: no classifier-free guidance (CFG) is used, enabled by ConditioningZeroOut feeding an intentionally empty negative conditioning. This keeps prompts straightforward (focus only on what you want), while ModelSamplingAuraFlow and KSampler deliver fast, stable results. The graph is organized into Model and Prompt groups for clarity, and uses PrimitiveInt/PrimitiveNode for quick edits to seed, steps, and duration.

The result is a tight, teachable text-to-music pipeline you can run repeatedly for variations or integrate as a reusable subgraph.

질문과 답변