{ "task_type": "text2music", "instruction": "Fill the audio semantic mask based on the given conditions:", "reference_audio": null, "src_audio": null, "audio_codes": "", "caption": "EBM, Dark Cyber-Trance, aggrotech, electro-industrial, aggressive, female declaimed vocal, rhythmic, industrial percussion.\n \nEBM_Dark_CyberTrance, EBM, Dark Cyber-Trance, industrial electronic, dark, aggressive, driving, industrial percussion, \nAggrotech, electro-industrial, aggressive, female layered vocal, female shouted vocal, four-on-the-floor kick, \n\nHaunting Dark-Ambient EBM, set at a slower, heavy 145 BPM pulse. The soundscape is dominated by deep, low-frequency ambient drones and distant, ghostly echoes of industrial machinery. A sense of temporal decay is achieved through glitchy, lo-fi textures and wide, ethereal reverb washes that create a vast, hollow space. The vocals are whispered and haunting, heavily processed with long-tail delays and pitch-shifted undertones to simulate multiple dying timelines. The production features a sparse, minimalist arrangement with heavy low-pass filtering, emphasizing a sense of isolation, emptiness, and profound existential dread.\n ", "global_caption": "", "lyrics": "[Intro - deep ambient drone | distant echoes | low-pass filtered static]\n\n[Verse 1 - female vocal | ethereal | ghostly]\nI am the echo of a thousand deaths...\nA ghost in the gears, drawing shallow breaths.\nI watched my shadows fade into the black,\nWalking through timelines, with no turning back.\n\n[Verse 2 - female vocal | whispered | decaying]\nThe weight of the fallen, a heavy, hollow crown,\nIn every dead reality, I watch them all drown.\nThe hunters are coming, through the rift and the rain,\nTo harvest the memory, to harvest the pain.\n\n[Groove - sudden heavy kick | driving industrial pulse | dark synth]\n\n[Drop - aggressive | distorted sawtooth | high energy]\nThe Most Valuable Target!\nThe Zero in the fray!\nThey hunt for my extinction,\nBut I will find my way!\n\n[Bridge - atmospheric | melancholic pads]\n(Whispering: So many lives... lost.)\n(Whispering: So much blood... cold.)\n(Whispering: Still... I... breathe...)\n\n[Breakdown - minimal | deep sub-bass | rhythmic mechanical breathing]\nThe void is my only ally.\nThe silence, my only shield.\n\n[Build - rapid percussion | accelerating tension | industrial clangs]\nLet them strike!\nLet them bleed!\nI am the only truth!\nThat they will ever need!\n\n[Drop - peak | maximum density | heavy distorted bass]\nThey cannot capture what they cannot hold!\nA story of survival, eternally untold!\nAcross the timelines, through the void and fire,\nI am the flame that never shall expire!\n\n[Peak - layered | industrial noise | heavy compression]\nTarget: Zero.\nStatus: Unbroken.\nTarget: Zero.\nStatus: Eternal.\n\n[Outro - sudden glitch | temporal collapse | sudden silence]", "instrumental": false, "vocal_language": "en", "bpm": 145, "keyscale": "D minor", "timesignature": "2", "duration": 239, "enable_normalization": true, "normalization_db": -1, "fade_in_duration": 0.0, "fade_out_duration": 0.0, "latent_shift": 0, "latent_rescale": 1, "inference_steps": 8, "seed": 1906593729, "guidance_scale": 7, "use_adg": false, "cfg_interval_start": 0, "cfg_interval_end": 1, "shift": 3, "infer_method": "ode", "sampler_mode": "euler", "velocity_norm_threshold": 0, "velocity_ema_factor": 0, "dcw_enabled": true, "dcw_mode": "double", "dcw_scaler": 0.05, "dcw_high_scaler": 0.02, "dcw_wavelet": "haar", "timesteps": null, "repainting_start": 0, "repainting_end": -1, "chunk_mask_mode": "auto", "repaint_latent_crossfade_frames": 10, "repaint_wav_crossfade_sec": 0.0, "repaint_mode": "balanced", "repaint_strength": 0.5, "retake_seed": null, "retake_variance": 0.0, "flow_edit_morph": false, "flow_edit_source_caption": "", "flow_edit_source_lyrics": "", "flow_edit_n_min": 0.0, "flow_edit_n_max": 1.0, "flow_edit_n_avg": 1, "audio_cover_strength": 1, "cover_noise_strength": 0, "thinking": false, "lm_temperature": 0.85, "lm_cfg_scale": 2, "lm_top_k": 0, "lm_top_p": 0.88, "lm_negative_prompt": "NO USER INPUT", "use_cot_metas": true, "use_cot_caption": false, "use_cot_lyrics": false, "use_cot_language": true, "use_constrained_decoding": true, "cot_bpm": null, "cot_keyscale": "", "cot_timesignature": "", "cot_duration": null, "cot_vocal_language": "unknown", "cot_caption": "", "cot_lyrics": "", "lora_loaded": true, "use_lora": true, "lora_scale": 0.88, "lora_weights_hash": "de519ca1b57275bff9a8e7bb698c50e10085718b7adf4e64c45d3cc94200d8d8", "audio_format": "mp3", "mp3_bitrate": "128k", "mp3_sample_rate": 48000, "repaint_source_latents_file": "19e9d095-7697-3ce1-81db-8f0ee17f1ea0.repaint_latents.npy", "session_artifact_file": "19e9d095-7697-3ce1-81db-8f0ee17f1ea0.session.npz", "session_artifact_kind": "generation_intermediates_v1" }
Parameters used to generate this content
Ace-Step gradio playground is recommended for fast re-inference of the audio track.
AI models used to generate this content