{ "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, distorted synth bass, male declaimed vocal, male shouted vocal, rhythmic, industrial percussion.\n \nEBM_Dark_CyberTrance, EBM, Dark Cyber-Trance, industrial electronic, dark, aggressive, driving, industrial percussion, distorted synth bass, \nAggrotech, electro-industrial, aggressive, female layered vocal, female shouted vocal, four-on-the-floor kick, \n\n\nBrutalist surge of aggrotech, driven by a relentless four-on-the-floor kick and syncopated 16th-note hi-hats, punctuated by industrial-style sampled metal hits. Distorted analog synth basslines anchor the low end, while abrasive arpeggiated synth leads and dark pad washes build a claustrophobic, dystopian soundscape. A gritty male vocal delivers an aggressive, declaimed performance, heavily processed with distortion and delay. The production features a compressed wall-of-sound with noticeable sidechain pumping and tape saturation, creating a polished yet overdriven mix. The track's progression is cyclical, building tension into explosive, high-energy drops.\n ", "global_caption": "", "lyrics": "[Intro - mechanical | pulsing synth entry]\n\n[Groove - driving | four-on-the-floor kick enters]\n\n[Verse 1 - male vocal | processed]\nHabĂa una vez un ciborg\nque querĂa robar mucho\nmucho mucho querĂa robar\nque se hizo dictador\n\n[Verse 2 - male vocal | processed]\nEstaba dictando cuando\nde repente pensĂł\nsi se cansarĂa de dictar\npero se dio cuenta de que\nsi aquel no dicta, otro lo hará\n\n[Groove - female vocal filtered]\n\n[Drop - peak | male and female vocals | maximum density]\nMáquinas hechas para robar\nrobo incansable, roba sin dudar\nMáquinas hechas para robar\nrobo incansable, roba sin dudar\n\n[Break - driving | Atmosferic]\n\n[Build - driving | male and female vocals]\nHabĂa una vez un ciborg\nque querĂa robar mucho\nmucho mucho querĂa robar\nque se hizo dictador\n\n[Drop - peak | male and female vocals | maximum density]\nMáquinas hechas para robar\nrobo incansable, roba sin dudar\nMáquinas hechas para robar\nrobo incansable, roba sin dudar\n\n[Drop - peak | male and female vocals | maximum density]\nMáquinas hechas para robar\nrobo incansable, roba sin dudar\nMáquinas hechas para robar\nrobo incansable, roba sin dudar\n\n[Outro - fade out]\n", "instrumental": false, "vocal_language": "es", "bpm": 162, "keyscale": "G# minor", "timesignature": "", "duration": -1, "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": 824031528, "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": 0.9, "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": "4", "cot_duration": 242.0, "cot_vocal_language": "unknown", "cot_caption": "", "cot_lyrics": "", "lora_loaded": true, "use_lora": true, "lora_scale": 0.8, "lora_weights_hash": "de519ca1b57275bff9a8e7bb698c50e10085718b7adf4e64c45d3cc94200d8d8", "audio_format": "mp3", "mp3_bitrate": "128k", "mp3_sample_rate": 48000, "repaint_source_latents_file": "ab0c8fc9-bf39-71ea-362e-202c4d82d018.repaint_latents.npy", "session_artifact_file": "ab0c8fc9-bf39-71ea-362e-202c4d82d018.session.npz", "session_artifact_kind": "generation_intermediates_v1" }
Parameters used to generate this content
beware duration is 242 Ace-Step gradio playground is recommended for fast re-inference of the audio track.
AI models used to generate this content