ACE-Step 1.5 Music Generation (4B LLM )

# 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": 128,
            "cfg_scale": 2,
            "clip": [
                "105",
                0
            ],
            "duration": 120,
            "generate_audio_codes": True,
            "keyscale": "E minor",
            "language": "en",
            "lyrics": "[Intro]\n\n[Verse 1]\nHeadlights on the coastline, the city falls behind\nRadio is humming every word that's on my mind\nMile after mile the ocean keeps the time\nYour hand out the window, catching starlight\n\n[Pre-Chorus]\nDon't slow down, don't look back\nThe night is ours on this empty track\n\n[Chorus]\nWe're driving into midnight, chasing neon skies\nEvery exit's calling but we never say goodbye\nHold on to the moment, let the engine sing\nWe're driving into midnight, we can have anything\n\n[Verse 2]\nTail lights like a heartbeat pulsing in the rain\nSaltwater on the windshield, nothing stays the same\nTurn the music louder, let the static fade\nEvery curve is golden, every fear is gone\n\n[Bridge]\nAnd when the morning finds us\nWe'll still be singing\n\n[Chorus]\nWe're driving into midnight, chasing neon skies\nEvery exit's calling but we never say goodbye\nHold on to the moment, let the engine sing\nWe're driving into midnight, we can have anything\n\n[Outro]",
            "min_p": 0,
            "seed": 31,
            "tags": "Upbeat modern electro-synthpop with a driving 128 BPM tempo. Mood evolves from moody nocturnal anticipation into euphoric, bittersweet catharsis. Production style features hyper-compressed sidechain pumping, warm tube saturation, and an expansive stereo field. \n\nInstrumentation: Punchy four-on-the-floor hybrid drums, aggressive sidechained sawtooth bass, shimmering analog polyphonic pads, and crystalline lead synthesizers.\n\nArrangement:\n- Intro: Low-pass filtered drum groove beneath swelling atmospheric pads.\n- Verse: Driving bassline and rhythmic muted guitar stabs under an intimate, emotive male vocal.\n- Chorus: Full explosive dynamic lift featuring soaring multi-tracked vocal harmonies singing an anthemic hook about driving at night, accompanied by bright supersaw synth leads and crisp claps.\n- Bridge: Atmospheric half-time breakdown featuring resonant filter sweeps and vocoder textures.\n- Outro: Driving high-energy reprise gradually stripping back to the core rhythm, ending on a sustained reverb tail.",
            "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": 120
        },
        "_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_4b_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)