ACE-Step 1.5 音樂產生工作流程
輸入一個描述音樂風格和可選歌詞的文字提示詞。在消費級硬體上,不到10秒即可產生一首完整、高品質的音訊歌曲。
下載工作流程在 Cloud 中試用 API 文件
00:00
工作流程內部
來源範本的唯讀預覽。請在 Cloud 中開啟,以探索節點並進行變更。
從您的程式碼呼叫此模型
以下請求使用與 Playground 相同的已準備節點圖和設定。每次提交都可能啟動付費執行;若提交結果不明,請勿自動重試提交。
1 取得 API 金鑰 ↗
What you need
- Runs on
- Comfy Cloud
- 金鑰
- COMFY_API_KEY
需要付費 Cloud 方案與點數。
下載 API JSONAPI 文件 ↗
# Python 3.10+: pip install comfy-sdk==0.4.0
import os
from comfy_sdk import Comfy
api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
"3": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 1,
"latent_image": [
"98",
0
],
"model": [
"78",
0
],
"negative": [
"47",
0
],
"positive": [
"94",
0
],
"sampler_name": "euler",
"scheduler": "simple",
"seed": 31,
"steps": 8
},
"_meta": {
"title": "KSampler"
}
},
"18": {
"class_type": "VAEDecodeAudio",
"inputs": {
"samples": [
"3",
0
],
"vae": [
"106",
0
]
},
"_meta": {
"title": "VAE Decode Audio"
}
},
"47": {
"class_type": "ConditioningZeroOut",
"inputs": {
"conditioning": [
"94",
0
]
},
"_meta": {
"title": "Conditioning Zero Out"
}
},
"78": {
"class_type": "ModelSamplingAuraFlow",
"inputs": {
"model": [
"104",
0
],
"sampling": "flow",
"shift": 3
},
"_meta": {
"title": "ModelSamplingAuraFlow"
}
},
"94": {
"class_type": "TextEncodeAceStepAudio1.5",
"inputs": {
"bpm": 195,
"cfg_scale": 2,
"clip": [
"105",
0
],
"duration": 75,
"generate_audio_codes": True,
"keyscale": "E minor",
"language": "en",
"lyrics": "[Intro]\n\n[Verse 1]\nConcrete cracked and the summer's gone\nWheels on fire since the break of dawn\nNobody's waiting at the end of the street\nJust the hum of the city and the sound of our feet\n\n[Chorus]\nHey! Hey! Never slowing down!\nHey! Hey! Burn across this town!\n\n[Verse 2]\nRusted rails and a broken fence\nEvery bruise is a souvenir of sense\nCoast on the edge of the parking lot light\nWe don't need a reason, we just need the night\n\n[Chorus]\nHey! Hey! Never slowing down!\nHey! Hey! Burn across this town!\n\n[Outro]",
"min_p": 0,
"seed": 31,
"tags": "Genre: Fast-paced 1990s skate punk.\nTempo: 195 BPM.\nKey: E minor.\nMood: Raw, frantic aggression that builds into triumphant catharsis.\nProduction Style: Dry, abrasive basement demo production with biting midrange and saturated transient punch.\nInstrumentation: Searing buzzsaw lead electric guitar, overdriven solid-body rhythm guitar, gritty picked electric bass, and a pummeling drum kit heavy on tight snare rolls and bright crash cymbals.\nArrangement:\n- Intro: Blistering drum fill into a high-speed descending lead guitar run.\n- Verse: Rapid palm-muted power chords over a driving, walking bassline and urgent double-time beat.\n- Chorus: Explosive, wide open chords driven by raw, passionate, shouted group vocals chanting a short English refrain.\n- Outro: Sudden syncopated full-band stop accented by a harsh burst of trailing amplifier feedback.",
"temperature": 0.85,
"timesignature": "4",
"top_k": 0,
"top_p": 0.9
},
"_meta": {
"title": "TextEncodeAceStepAudio1.5"
}
},
"98": {
"class_type": "EmptyAceStep1.5LatentAudio",
"inputs": {
"batch_size": 1,
"seconds": 75
},
"_meta": {
"title": "Empty Ace Step 1.5 Latent Audio"
}
},
"104": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "acestep_v1.5_turbo.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model"
}
},
"105": {
"class_type": "DualCLIPLoader",
"inputs": {
"clip_name1": "qwen_0.6b_ace15.safetensors",
"clip_name2": "qwen_1.7b_ace15.safetensors",
"device": "default",
"type": "ace"
},
"_meta": {
"title": "Load CLIP (Dual)"
}
},
"106": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "ace_1.5_vae.safetensors"
},
"_meta": {
"title": "Load VAE"
}
},
"107": {
"class_type": "SaveAudioMP3",
"inputs": {
"audio": [
"18",
0
],
"filename_prefix": "audio/ComfyUI",
"quality": "V0"
},
"_meta": {
"title": "Save Audio (MP3) (DEPRECATED)"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)
for output in job.get_outputs("107"):
output.to_file(output.name)試試範例
關於此工作流程
ACE-Step 1.5 音樂生成工作流程旨在用一般消費級硬體,將文字提示詞在數秒內轉成高品質音訊歌曲。此工作流程使用 ACE-Step 模型,特別是「acestep_v1.5_turbo.safetensors」,用來理解並合成你描述的音樂風格與可選的歌詞。TextEncodeAceStepAudio1.5 與 VAEDecodeAudio 等關鍵節點分別負責編碼文字輸入與解碼生成的音訊。KSampler 節點用於對潛在空間進行取樣,而 ModelSamplingAuraFlow 則用於精修音訊輸出,以符合高品質標準。
此工作流程的優勢在於效率與輸出品質。透過 ConditioningZeroOut 與 EmptyAceStep1.5LatentAudio 等節點,流程能維持精簡並聚焦於使用者輸入。並且透過 SaveAudioMP3 節點,可將最終成品直接匯出為相容性高的 MP3 格式,適合用於多種應用情境。
問答
包含音樂風格、情緒與可選歌詞的描述性提示效果最佳。
可以,請用流程中的 PrimitiveNode 設定所需長度。
生成音樂會以 MP3 格式儲存,支援大多數播放器。
可以,流程已針對一般消費級硬體(含舊機種)最佳化。
相關工作流程
- AACE-Step
ACE Step v1 M2M編輯
- AACE-Step
ACE Step v1文字到歌曲
- AACE-Step, Google Gemini
ACE-Step 1.5 AI 歌詞歌曲產生
- AACE-Step
ACE-Step 1.5 音樂產生 AIO
- AACE-Step
ACE-Step 1.5 音樂產生(4B LLM)
- AACE-Step
ACE-Step 1.5XL SFT:文生音樂
- AACE-Step
ACE-Step 1.5XL Turbo:文字轉音樂
- AACE-Step
ACE-Step 1.5XL 基礎版:文字轉音樂
- AACE-Step
ACE-Step v1文字到器樂音樂
- AACE-Step
文字轉歌曲(新版)