{ "parity_find": { "requests": [ { "task_type": "text2music", "caption": "warm analog synth pop with female vocals", "lyrics": "[verse]\nwe build the night from neon air\n[chorus]\nturn the city into sound", "instrumental": false, "duration": 10, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "en", "seed": 1234, "inference_steps": 1, "guidance_scale": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 }, { "task_type": "text2music", "caption": "soft piano ballad with intimate vocals", "lyrics": "[verse]\nslow light on the window glass\n[chorus]\nhold the quiet while it lasts", "instrumental": false, "duration": 5, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "en", "seed": 1234, "inference_steps": 1, "guidance_scale": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "default": { "requests": [ { "task_type": "text2music", "caption": "upbeat electronic instrumental with bright synths and punchy drums", "lyrics": "[Instrumental]", "instrumental": true, "duration": 10, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "en", "seed": 0, "inference_steps": 1, "guidance_scale": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "extract_vocals_mel_roformer_15s": { "assert_optional_request_fields": [ "task_type", "src_audio", "instruction", "negative_prompt", "track_name", "use_cot_metas", "use_cot_caption", "use_cot_language", "shift", "infer_method", "audio_cover_strength", "cover_noise_strength", "use_adg", "cfg_interval_start", "cfg_interval_end", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "dcw_enabled" ], "requests": [ { "task_type": "extract", "caption": "vocals", "lyrics": "", "instrumental": false, "instruction": "Extract the VOCALS track from the audio:", "negative_prompt": "NO USER INPUT", "src_audio": "resources/mel_roformer_test_15s.wav", "track_name": "vocals", "duration": 15, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "seed": 1234, "inference_steps": 50, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 3.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "cover_mel_roformer_10s": { "assert_optional_request_fields": [ "task_type", "src_audio", "instruction", "negative_prompt", "bpm", "keyscale", "timesignature", "use_cot_metas", "use_cot_caption", "use_cot_language", "shift", "infer_method", "audio_cover_strength", "cover_noise_strength", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "dcw_enabled" ], "requests": [ { "task_type": "cover", "caption": "Transform the source audio into a bright synth-pop cover with clear lead vocals, tight electronic drums, warm bass, and polished chorus energy while preserving the source melody structure.", "lyrics": "[Verse]\nMorning lights across the room\n[Chorus]\nTurn the melody into bloom", "instrumental": false, "instruction": "Generate audio semantic tokens based on the given conditions:", "negative_prompt": "NO USER INPUT", "src_audio": "resources/mel_roformer_test_10s.wav", "duration": 10, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 120, "keyscale": "C major", "timesignature": "4", "seed": 1234, "inference_steps": 10, "guidance_scale": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "base_cover_mel_roformer_10s": { "assert_optional_request_fields": [ "task_type", "src_audio", "instruction", "negative_prompt", "bpm", "keyscale", "timesignature", "use_cot_metas", "use_cot_caption", "use_cot_language", "shift", "infer_method", "audio_cover_strength", "cover_noise_strength", "use_adg", "cfg_interval_start", "cfg_interval_end", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "dcw_enabled" ], "requests": [ { "task_type": "cover", "caption": "Transform the source audio into a bright synth-pop cover with clear lead vocals, tight electronic drums, warm bass, and polished chorus energy while preserving the source melody structure.", "lyrics": "[Verse]\nMorning lights across the room\n[Chorus]\nTurn the melody into bloom", "instrumental": false, "instruction": "Generate audio semantic tokens based on the given conditions:", "negative_prompt": "NO USER INPUT", "src_audio": "resources/mel_roformer_test_10s.wav", "duration": 10, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 120, "keyscale": "C major", "timesignature": "4", "seed": 1234, "inference_steps": 50, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 3.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "base_cover_nofsq_mel_roformer_10s": { "assert_optional_request_fields": [ "task_type", "src_audio", "instruction", "negative_prompt", "bpm", "keyscale", "timesignature", "use_cot_metas", "use_cot_caption", "use_cot_language", "shift", "infer_method", "audio_cover_strength", "cover_noise_strength", "use_adg", "cfg_interval_start", "cfg_interval_end", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "dcw_enabled" ], "requests": [ { "task_type": "cover-nofsq", "caption": "Transform the source audio into a bright synth-pop cover with clear lead vocals, tight electronic drums, warm bass, and polished chorus energy while preserving the source melody structure.", "lyrics": "[Verse]\nMorning lights across the room\n[Chorus]\nTurn the melody into bloom", "instrumental": false, "instruction": "Generate audio semantic tokens based on the given conditions:", "negative_prompt": "NO USER INPUT", "src_audio": "resources/mel_roformer_test_10s.wav", "duration": 10, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 120, "keyscale": "C major", "timesignature": "4", "seed": 1234, "inference_steps": 50, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 3.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "base_repaint_mel_roformer_10s": { "assert_optional_request_fields": [ "task_type", "src_audio", "instruction", "negative_prompt", "chunk_mask_mode", "repainting_start", "repainting_end", "use_cot_metas", "use_cot_caption", "use_cot_language", "shift", "infer_method", "audio_cover_strength", "cover_noise_strength", "use_adg", "cfg_interval_start", "cfg_interval_end", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "repaint_mode", "repaint_strength", "dcw_enabled" ], "requests": [ { "task_type": "repaint", "caption": "Repaint only the middle window into a clean full-band pop section with clear vocal lead, steady drums, warm bass, and smooth transitions back into the source audio.", "lyrics": "[Verse]\nMorning lights across the room\n[Chorus]\nTurn the melody into bloom", "instrumental": false, "instruction": "Repaint the mask area based on the given conditions:", "negative_prompt": "NO USER INPUT", "src_audio": "resources/mel_roformer_test_10s.wav", "duration": 10, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 120, "keyscale": "C major", "timesignature": "4", "chunk_mask_mode": "explicit", "repainting_start": 2.0, "repainting_end": 6.0, "seed": 1234, "inference_steps": 50, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 3.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "repaint_mode": "balanced", "repaint_strength": 0.5, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "base_repaint_mel_roformer_12s": { "assert_optional_request_fields": [ "task_type", "src_audio", "instruction", "negative_prompt", "chunk_mask_mode", "repainting_start", "repainting_end", "use_cot_metas", "use_cot_caption", "use_cot_language", "shift", "infer_method", "audio_cover_strength", "cover_noise_strength", "use_adg", "cfg_interval_start", "cfg_interval_end", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "repaint_mode", "repaint_strength", "dcw_enabled" ], "requests": [ { "task_type": "repaint", "caption": "Repaint the center of this longer music excerpt into a polished pop section with a clear vocal lead, steady drums, warm bass, and smooth transitions back into the source audio.", "lyrics": "[Verse]\nMorning lights across the room\n[Chorus]\nTurn the melody into bloom", "instrumental": false, "instruction": "Repaint the mask area based on the given conditions:", "negative_prompt": "NO USER INPUT", "src_audio": "resources/mel_roformer_test_12s.wav", "duration": 12, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 120, "keyscale": "C major", "timesignature": "4", "chunk_mask_mode": "explicit", "repainting_start": 3.0, "repainting_end": 8.0, "seed": 1234, "inference_steps": 50, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 3.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "repaint_mode": "balanced", "repaint_strength": 0.5, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "base_repaint_mel_roformer_12s_then_10s": { "assert_optional_request_fields": [ "task_type", "src_audio", "instruction", "negative_prompt", "chunk_mask_mode", "repainting_start", "repainting_end", "use_cot_metas", "use_cot_caption", "use_cot_language", "shift", "infer_method", "audio_cover_strength", "cover_noise_strength", "use_adg", "cfg_interval_start", "cfg_interval_end", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "repaint_mode", "repaint_strength", "dcw_enabled" ], "requests": [ { "task_type": "repaint", "caption": "Repaint the center of this longer music excerpt into a polished pop section with a clear vocal lead, steady drums, warm bass, and smooth transitions back into the source audio.", "lyrics": "[Verse]\nMorning lights across the room\n[Chorus]\nTurn the melody into bloom", "instrumental": false, "instruction": "Repaint the mask area based on the given conditions:", "negative_prompt": "NO USER INPUT", "src_audio": "resources/mel_roformer_test_12s.wav", "duration": 12, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 120, "keyscale": "C major", "timesignature": "4", "chunk_mask_mode": "explicit", "repainting_start": 3.0, "repainting_end": 8.0, "seed": 1234, "inference_steps": 50, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 3.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "repaint_mode": "balanced", "repaint_strength": 0.5, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 }, { "task_type": "repaint", "caption": "Repaint only the middle window into a clean full-band pop section with clear vocal lead, steady drums, warm bass, and smooth transitions back into the source audio.", "lyrics": "[Verse]\nMorning lights across the room\n[Chorus]\nTurn the melody into bloom", "instrumental": false, "instruction": "Repaint the mask area based on the given conditions:", "negative_prompt": "NO USER INPUT", "src_audio": "resources/mel_roformer_test_10s.wav", "duration": 10, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 120, "keyscale": "C major", "timesignature": "4", "chunk_mask_mode": "explicit", "repainting_start": 2.0, "repainting_end": 6.0, "seed": 1234, "inference_steps": 50, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 3.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "repaint_mode": "balanced", "repaint_strength": 0.5, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "base_repaint_mel_roformer_10s_then_15s": { "assert_optional_request_fields": [ "task_type", "src_audio", "instruction", "negative_prompt", "chunk_mask_mode", "repainting_start", "repainting_end", "use_cot_metas", "use_cot_caption", "use_cot_language", "shift", "infer_method", "audio_cover_strength", "cover_noise_strength", "use_adg", "cfg_interval_start", "cfg_interval_end", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "repaint_mode", "repaint_strength", "dcw_enabled" ], "requests": [ { "task_type": "repaint", "caption": "Repaint only the middle window into a clean full-band pop section with clear vocal lead, steady drums, warm bass, and smooth transitions back into the source audio.", "lyrics": "[Verse]\nMorning lights across the room\n[Chorus]\nTurn the melody into bloom", "instrumental": false, "instruction": "Repaint the mask area based on the given conditions:", "negative_prompt": "NO USER INPUT", "src_audio": "resources/mel_roformer_test_10s.wav", "duration": 10, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 120, "keyscale": "C major", "timesignature": "4", "chunk_mask_mode": "explicit", "repainting_start": 2.0, "repainting_end": 6.0, "seed": 1234, "inference_steps": 50, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 3.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "repaint_mode": "balanced", "repaint_strength": 0.5, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 }, { "task_type": "repaint", "caption": "Repaint the center of this longer music excerpt into a polished pop section with a clear vocal lead, steady drums, warm bass, and smooth transitions back into the source audio.", "lyrics": "[Verse]\nMorning lights across the room\n[Chorus]\nTurn the melody into bloom", "instrumental": false, "instruction": "Repaint the mask area based on the given conditions:", "negative_prompt": "NO USER INPUT", "src_audio": "resources/mel_roformer_test_15s.wav", "duration": 15, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 120, "keyscale": "C major", "timesignature": "4", "chunk_mask_mode": "explicit", "repainting_start": 3.0, "repainting_end": 10.0, "seed": 1234, "inference_steps": 50, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 3.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "repaint_mode": "balanced", "repaint_strength": 0.5, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "base_repaint_mel_roformer_180s_smoke": { "assert_optional_request_fields": [ "task_type", "src_audio", "instruction", "negative_prompt", "chunk_mask_mode", "repainting_start", "repainting_end", "use_cot_metas", "use_cot_caption", "use_cot_language", "shift", "infer_method", "audio_cover_strength", "cover_noise_strength", "use_adg", "cfg_interval_start", "cfg_interval_end", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "repaint_mode", "repaint_strength", "dcw_enabled" ], "requests": [ { "task_type": "repaint", "caption": "Repaint the center of this long music excerpt into a polished pop section with a clear vocal lead, steady drums, warm bass, and smooth transitions back into the source audio.", "lyrics": "[Verse]\nMorning lights across the room\n[Chorus]\nTurn the melody into bloom", "instrumental": false, "instruction": "Repaint the mask area based on the given conditions:", "negative_prompt": "NO USER INPUT", "src_audio": "resources/mel_roformer_test_180s.wav", "duration": 180, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 120, "keyscale": "C major", "timesignature": "4", "chunk_mask_mode": "explicit", "repainting_start": 45.0, "repainting_end": 120.0, "seed": 1234, "inference_steps": 5, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 3.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "repaint_mode": "balanced", "repaint_strength": 0.5, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "complete_all_optional_10s": { "assert_optional_request_fields": [ "task_type", "instruction", "negative_prompt", "src_audio", "track_name", "complete_track_classes", "bpm", "keyscale", "timesignature", "chunk_mask_mode", "use_cot_metas", "use_cot_caption", "use_cot_language", "lm_temperature", "lm_cfg_scale", "lm_top_k", "lm_top_p", "shift", "infer_method", "timesteps", "audio_cover_strength", "cover_noise_strength", "retake_seed", "retake_variance", "use_adg", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "cfg_interval_start", "cfg_interval_end", "dcw_enabled", "dcw_mode", "dcw_scaler", "dcw_high_scaler", "dcw_wavelet" ], "requests": [ { "task_type": "complete", "caption": "Complete this short vocal-forward music excerpt into a polished full-band section with steady bass, energetic drums, and a clear lead vocal.", "lyrics": "[Verse]\nHold the spark inside the night\n[Chorus]\nCarry the sound into the light", "instrumental": false, "instruction": "Complete the input track with VOCALS | DRUMS | BASS:", "negative_prompt": "NO USER INPUT", "src_audio": "tests/ace_step/assets/complete_source_demucs_8s.wav", "track_name": "vocals", "complete_track_classes": ["vocals", "drums", "bass"], "duration": 10, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "en", "bpm": 128, "keyscale": "C minor", "timesignature": "4", "chunk_mask_mode": "auto", "seed": 1234, "inference_steps": 5, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 1.0, "infer_method": "ode", "timesteps": [1.0, 0.75, 0.5, 0.25, 0.0], "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "retake_seed": 4321, "retake_variance": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": false, "dcw_mode": "double", "dcw_scaler": 0.05, "dcw_high_scaler": 0.02, "dcw_wavelet": "haar", "lm_temperature": 0.0, "lm_cfg_scale": 2.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "complete_src_audio_direct_10s": { "assert_optional_request_fields": [ "task_type", "instruction", "negative_prompt", "src_audio", "complete_track_classes", "bpm", "keyscale", "timesignature", "chunk_mask_mode", "use_cot_metas", "use_cot_caption", "use_cot_language", "lm_temperature", "lm_cfg_scale", "lm_top_k", "lm_top_p", "shift", "infer_method", "audio_cover_strength", "cover_noise_strength", "use_adg", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "cfg_interval_start", "cfg_interval_end", "dcw_enabled" ], "requests": [ { "task_type": "complete", "caption": "Complete this vocal-forward excerpt into a tight full-band pop section with a clear lead vocal, steady drums, and warm bass.", "lyrics": "[Verse]\nHold the spark inside the night\n[Chorus]\nCarry the sound into the light", "instrumental": false, "instruction": "Complete the input track with VOCALS | DRUMS | BASS:", "negative_prompt": "NO USER INPUT", "src_audio": "resources/mel_roformer_test_10s.wav", "complete_track_classes": ["vocals", "drums", "bass"], "duration": 10, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 128, "keyscale": "C minor", "timesignature": "4", "chunk_mask_mode": "auto", "seed": 5678, "inference_steps": 50, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": false, "lm_temperature": 0.0, "lm_cfg_scale": 2.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "complete_no_source_audio_10s": { "assert_optional_request_fields": [ "task_type", "instruction", "negative_prompt", "complete_track_classes", "bpm", "keyscale", "timesignature", "chunk_mask_mode", "use_cot_metas", "use_cot_caption", "use_cot_language", "lm_temperature", "lm_cfg_scale", "lm_top_k", "lm_top_p", "shift", "infer_method", "audio_cover_strength", "cover_noise_strength", "use_adg", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "cfg_interval_start", "cfg_interval_end", "dcw_enabled" ], "requests": [ { "task_type": "complete", "caption": "Complete a short upbeat pop section with clear lead vocals, steady drums, warm bass, and bright guitar accents.", "lyrics": "[Verse]\nHold the spark inside the night\n[Chorus]\nCarry the sound into the light", "instrumental": false, "instruction": "Complete the input track with VOCALS | DRUMS | BASS:", "negative_prompt": "NO USER INPUT", "complete_track_classes": ["vocals", "drums", "bass"], "duration": 10, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 128, "keyscale": "C minor", "timesignature": "4", "chunk_mask_mode": "auto", "seed": 5678, "inference_steps": 30, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 1.0, "infer_method": "ode", "timesteps": [1.0, 0.9666667, 0.9333333, 0.9, 0.8666667, 0.8333333, 0.8, 0.7666667, 0.7333333, 0.7, 0.6666667, 0.6333333, 0.6, 0.5666667, 0.5333333, 0.5, 0.4666667, 0.4333333, 0.4, 0.3666667, 0.3333333, 0.3, 0.2666667, 0.2333333, 0.2, 0.1666667, 0.1333333, 0.1, 0.0666667, 0.0333333, 0.0], "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": false, "lm_temperature": 0.0, "lm_cfg_scale": 2.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "lego_guitar_from_piano_10s": { "assert_optional_request_fields": [ "task_type", "instruction", "src_audio", "track_name", "chunk_mask_mode", "repainting_start", "repainting_end", "use_cot_metas", "use_cot_caption", "use_cot_language", "lm_temperature", "lm_cfg_scale", "lm_top_k", "lm_top_p", "shift", "infer_method", "audio_cover_strength", "cover_noise_strength", "use_adg", "sampler_mode", "velocity_norm_threshold", "velocity_ema_factor", "cfg_interval_start", "cfg_interval_end", "dcw_enabled" ], "requests": [ { "task_type": "lego", "caption": "Add a bright, rhythmic electric guitar layer that follows the piano harmony and gives the track a clear pop-rock lift.", "lyrics": "[Instrumental]", "instrumental": true, "instruction": "Generate the GUITAR track based on the audio context:", "src_audio": "resources/mel_roformer_test_10s.wav", "track_name": "guitar", "duration": 10, "thinking": false, "use_cot_metas": false, "use_cot_caption": false, "use_cot_language": false, "vocal_language": "en", "bpm": 100, "keyscale": "C major", "timesignature": "4", "chunk_mask_mode": "auto", "repainting_start": 0.0, "repainting_end": -1.0, "seed": 1234, "inference_steps": 50, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 3.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": false, "lm_temperature": 0.0, "lm_cfg_scale": 1.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "reference_text2music_example_01": { "requests": [ { "task_type": "text2music", "caption": "An explosive, high-energy pop-rock track with a strong anime theme song feel. The song kicks off with a catchy, synthesized brass fanfare over a driving rock beat with punchy drums and a solid bassline. A powerful, clear male vocal enters with a theatrical and energetic delivery, soaring through the verses and hitting powerful high notes in the chorus. The arrangement is dense and dynamic, featuring rhythmic electric guitar chords, brief instrumental breaks with synth flourishes, and a consistent, danceable groove throughout. The overall mood is triumphant, adventurous, and exhilarating.", "lyrics": "[Intro - Synth Brass Fanfare]\n\n[Verse 1]\n黑夜里的风吹过耳畔\n甜蜜时光转瞬即万\n脚步飘摇在星光上\n心追节奏心跳狂乱\n耳边传来电吉他呼唤\n手指轻触碰点流点燃\n梦在云端任它蔓延\n疯狂跳跃自由无间\n\n[Chorus]\n心电感应在震动间\n拥抱未来勇敢冒险\n那旋律在心中无限\n世界变得如此耀眼\n\n[Instrumental Break - Synth Brass Melody]\n\n[Verse 2]\n鼓点撞击黑夜的底端\n跳动节拍连接你我俩\n在这里让灵魂发光\n燃尽所有不留遗憾\n\n[Instrumental Break - Synth Brass Melody]\n\n[Bridge]\n光影交错彼此的视线\n霓虹之下夜空的蔚蓝\n月光洒下温热心田\n追逐梦想它不会遥远\n\n[Chorus]\n心电感应在震动间\n拥抱未来勇敢冒险\n那旋律在心中无限\n世界变得如此耀眼\n\n[Outro - Instrumental with Synth Brass Melody]\n[Song ends abruptly]", "instrumental": false, "duration": 160, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "zh", "bpm": 100, "keyscale": "B minor", "timesignature": "4", "seed": 1234, "inference_steps": 8, "guidance_scale": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": true, "dcw_mode": "double", "dcw_scaler": 0.05, "dcw_high_scaler": 0.02, "dcw_wavelet": "haar", "lm_temperature": 0.0, "lm_cfg_scale": 2.0, "lm_top_k": 0, "lm_top_p": 0.9 } ] }, "reference_text2music_example_01_600s_temp0": { "requests": [ { "task_type": "text2music", "caption": "An explosive, high-energy pop-rock track with a strong anime theme song feel. The song kicks off with a catchy, synthesized brass fanfare over a driving rock beat with punchy drums and a solid bassline. A powerful, clear male vocal enters with a theatrical and energetic delivery, soaring through the verses and hitting powerful high notes in the chorus. The arrangement is dense and dynamic, featuring rhythmic electric guitar chords, brief instrumental breaks with synth flourishes, and a consistent, danceable groove throughout. The overall mood is triumphant, adventurous, and exhilarating.", "lyrics": "[Intro - Synth Brass Fanfare]\n\n[Verse 1]\n黑夜里的风吹过耳畔\n甜蜜时光转瞬即万\n脚步飘摇在星光上\n心追节奏心跳狂乱\n耳边传来电吉他呼唤\n手指轻触碰点流点燃\n梦在云端任它蔓延\n疯狂跳跃自由无间\n\n[Chorus]\n心电感应在震动间\n拥抱未来勇敢冒险\n那旋律在心中无限\n世界变得如此耀眼\n\n[Instrumental Break - Synth Brass Melody]\n\n[Verse 2]\n鼓点撞击黑夜的底端\n跳动节拍连接你我俩\n在这里让灵魂发光\n燃尽所有不留遗憾\n\n[Instrumental Break - Synth Brass Melody]\n\n[Bridge]\n光影交错彼此的视线\n霓虹之下夜空的蔚蓝\n月光洒下温热心田\n追逐梦想它不会遥远\n\n[Chorus]\n心电感应在震动间\n拥抱未来勇敢冒险\n那旋律在心中无限\n世界变得如此耀眼\n\n[Outro - Instrumental with Synth Brass Melody]\n[Song ends abruptly]", "instrumental": false, "duration": 600, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "zh", "bpm": 100, "keyscale": "B minor", "timesignature": "4", "seed": 1234, "inference_steps": 8, "guidance_scale": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": true, "dcw_mode": "double", "dcw_scaler": 0.05, "dcw_high_scaler": 0.02, "dcw_wavelet": "haar", "lm_temperature": 0.0, "lm_cfg_scale": 2.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "reference_text2music_example_01_20s": { "requests": [ { "task_type": "text2music", "caption": "An explosive, high-energy pop-rock track with a strong anime theme song feel. The song kicks off with a catchy, synthesized brass fanfare over a driving rock beat with punchy drums and a solid bassline. A powerful, clear male vocal enters with a theatrical and energetic delivery, soaring through the verses and hitting powerful high notes in the chorus. The arrangement is dense and dynamic, featuring rhythmic electric guitar chords, brief instrumental breaks with synth flourishes, and a consistent, danceable groove throughout. The overall mood is triumphant, adventurous, and exhilarating.", "lyrics": "[Intro - Synth Brass Fanfare]\n\n[Verse 1]\n黑夜里的风吹过耳畔\n甜蜜时光转瞬即万\n脚步飘摇在星光上\n心追节奏心跳狂乱\n耳边传来电吉他呼唤\n手指轻触碰点流点燃\n梦在云端任它蔓延\n疯狂跳跃自由无间\n\n[Chorus]\n心电感应在震动间\n拥抱未来勇敢冒险\n那旋律在心中无限\n世界变得如此耀眼\n\n[Instrumental Break - Synth Brass Melody]\n\n[Verse 2]\n鼓点撞击黑夜的底端\n跳动节拍连接你我俩\n在这里让灵魂发光\n燃尽所有不留遗憾\n\n[Instrumental Break - Synth Brass Melody]\n\n[Bridge]\n光影交错彼此的视线\n霓虹之下夜空的蔚蓝\n月光洒下温热心田\n追逐梦想它不会遥远\n\n[Chorus]\n心电感应在震动间\n拥抱未来勇敢冒险\n那旋律在心中无限\n世界变得如此耀眼\n\n[Outro - Instrumental with Synth Brass Melody]\n[Song ends abruptly]", "instrumental": false, "duration": 20, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "zh", "bpm": 100, "keyscale": "B minor", "timesignature": "4", "seed": 1234, "inference_steps": 8, "guidance_scale": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": true, "dcw_mode": "double", "dcw_scaler": 0.05, "dcw_high_scaler": 0.02, "dcw_wavelet": "haar", "lm_temperature": 0.0, "lm_cfg_scale": 2.0, "lm_top_k": 0, "lm_top_p": 0.9 } ] }, "base_text2music_jpop_chiptune_20s_cfg2": { "requests": [ { "task_type": "text2music", "caption": "An energetic, high-tempo J-pop and chiptune fusion track driven by a relentless four-on-the-floor drum machine beat and a pulsing synth bassline. The soundscape is dominated by bright, arpeggiated 8-bit style synthesizers that create a vibrant, video-game-like atmosphere. A clear, high-pitched female vocal delivers the melody with an upbeat, almost frantic energy, soaring over the dense electronic arrangement. The structure includes dynamic builds and drops, with a brief, atmospheric bridge featuring a whispered English vocal line before launching back into the powerful, synth-laden chorus and an instrumental synth-heavy outro.", "lyrics": "[Intro - Synth Arpeggio]\n\n[Verse 1]\n森の奥で芽吹く音\n素衣ざなたてが木が笑う\n流れてゆく時の中で\nそれたちの声が踊り出す\n\n[Pre-Chorus]\n鳥が歌えば風がふわりと\n母の愛を運んできたよ\n子供たちの背中を追って\n深い森の上で生きる\n\n[Chorus]\n森の鳥語るよ\n好き君を想うその時に\n月夜の影忍び寄る\n静けさの中君を呼ぶ\n\n[Instrumental Break]\n\n[Verse 2]\n木の下で続く坂道\n鳥たちの声は夢を誘う\n絵を描いた木の夢\n木が叫ぶ運命の声\n\n[Pre-Chorus]\n時は流れて僕は行く\n名もない木は今もここに\n君がくれたそのぬくもり\n風がそっと背中を押す\n\n[Chorus]\n森の鳥語るよ\n好き君を想うその時に\n月夜の影忍び寄る\n静けさの中君を呼ぶ\n\n[Bridge]\n月の影に隠れた船\n季節巡り風が歌う\n風が呼ぶ声の先に\n静かにささやく君の名を\n\n[Breakdown]\n[whispered]\n響けその歌で\n静かに響く木の音\n\n[Instrumental Break]\n\n[Outro]\n森の奥の果てまで\n[Synth arpeggio fades out]", "instrumental": false, "duration": 20, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "ja", "bpm": 100, "keyscale": "F minor", "timesignature": "4", "seed": 1234, "inference_steps": 5, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": true, "dcw_mode": "double", "dcw_scaler": 0.05, "dcw_high_scaler": 0.02, "dcw_wavelet": "haar", "lm_temperature": 0.0, "lm_cfg_scale": 2.0, "lm_top_k": 0, "lm_top_p": 0.9 } ] }, "base_text2music_jpop_chiptune_20s_cfg2_ode_heun": { "requests": [ { "task_type": "text2music", "caption": "An energetic, high-tempo J-pop and chiptune fusion track driven by a relentless four-on-the-floor drum machine beat and a pulsing synth bassline. The soundscape is dominated by bright, arpeggiated 8-bit style synthesizers that create a vibrant, video-game-like atmosphere. A clear, high-pitched female vocal delivers the melody with an upbeat, almost frantic energy, soaring over the dense electronic arrangement. The structure includes dynamic builds and drops, with a brief, atmospheric bridge featuring a whispered English vocal line before launching back into the powerful, synth-laden chorus and an instrumental synth-heavy outro.", "lyrics": "[Intro - Synth Arpeggio]\n\n[Verse 1]\n森の奥で芽吹く音\n素衣ざなたてが木が笑う\n流れてゆく時の中で\nそれたちの声が踊り出す\n\n[Pre-Chorus]\n鳥が歌えば風がふわりと\n母の愛を運んできたよ\n子供たちの背中を追って\n深い森の上で生きる\n\n[Chorus]\n森の鳥語るよ\n好き君を想うその時に\n月夜の影忍び寄る\n静けさの中君を呼ぶ\n\n[Instrumental Break]\n\n[Verse 2]\n木の下で続く坂道\n鳥たちの声は夢を誘う\n絵を描いた木の夢\n木が叫ぶ運命の声\n\n[Pre-Chorus]\n時は流れて僕は行く\n名もない木は今もここに\n君がくれたそのぬくもり\n風がそっと背中を押す\n\n[Chorus]\n森の鳥語るよ\n好き君を想うその時に\n月夜の影忍び寄る\n静けさの中君を呼ぶ\n\n[Bridge]\n月の影に隠れた船\n季節巡り風が歌う\n風が呼ぶ声の先に\n静かにささやく君の名を\n\n[Breakdown]\n[whispered]\n響けその歌で\n静かに響く木の音\n\n[Instrumental Break]\n\n[Outro]\n森の奥の果てまで\n[Synth arpeggio fades out]", "instrumental": false, "duration": 20, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "ja", "bpm": 100, "keyscale": "F minor", "timesignature": "4", "seed": 1234, "inference_steps": 5, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "heun", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": true, "dcw_mode": "double", "dcw_scaler": 0.05, "dcw_high_scaler": 0.02, "dcw_wavelet": "haar", "lm_temperature": 0.0, "lm_cfg_scale": 2.0, "lm_top_k": 0, "lm_top_p": 0.9 } ] }, "base_text2music_jpop_chiptune_20s_cfg2_sde_euler": { "requests": [ { "task_type": "text2music", "caption": "An energetic, high-tempo J-pop and chiptune fusion track driven by a relentless four-on-the-floor drum machine beat and a pulsing synth bassline. The soundscape is dominated by bright, arpeggiated 8-bit style synthesizers that create a vibrant, video-game-like atmosphere. A clear, high-pitched female vocal delivers the melody with an upbeat, almost frantic energy, soaring over the dense electronic arrangement. The structure includes dynamic builds and drops, with a brief, atmospheric bridge featuring a whispered English vocal line before launching back into the powerful, synth-laden chorus and an instrumental synth-heavy outro.", "lyrics": "[Intro - Synth Arpeggio]\n\n[Verse 1]\n森の奥で芽吹く音\n素衣ざなたてが木が笑う\n流れてゆく時の中で\nそれたちの声が踊り出す\n\n[Pre-Chorus]\n鳥が歌えば風がふわりと\n母の愛を運んできたよ\n子供たちの背中を追って\n深い森の上で生きる\n\n[Chorus]\n森の鳥語るよ\n好き君を想うその時に\n月夜の影忍び寄る\n静けさの中君を呼ぶ\n\n[Instrumental Break]\n\n[Verse 2]\n木の下で続く坂道\n鳥たちの声は夢を誘う\n絵を描いた木の夢\n木が叫ぶ運命の声\n\n[Pre-Chorus]\n時は流れて僕は行く\n名もない木は今もここに\n君がくれたそのぬくもり\n風がそっと背中を押す\n\n[Chorus]\n森の鳥語るよ\n好き君を想うその時に\n月夜の影忍び寄る\n静けさの中君を呼ぶ\n\n[Bridge]\n月の影に隠れた船\n季節巡り風が歌う\n風が呼ぶ声の先に\n静かにささやく君の名を\n\n[Breakdown]\n[whispered]\n響けその歌で\n静かに響く木の音\n\n[Instrumental Break]\n\n[Outro]\n森の奥の果てまで\n[Synth arpeggio fades out]", "instrumental": false, "duration": 20, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "ja", "bpm": 100, "keyscale": "F minor", "timesignature": "4", "seed": 1234, "inference_steps": 5, "guidance_scale": 7.0, "use_adg": false, "cfg_interval_start": 0.0, "cfg_interval_end": 1.0, "shift": 1.0, "infer_method": "sde", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": true, "dcw_mode": "double", "dcw_scaler": 0.05, "dcw_high_scaler": 0.02, "dcw_wavelet": "haar", "lm_temperature": 0.0, "lm_cfg_scale": 2.0, "lm_top_k": 0, "lm_top_p": 0.9 } ] }, "lyric_text2music": { "requests": [ { "task_type": "text2music", "caption": "A smooth, contemporary R&B track built on a foundation of clean, chorused electric guitar chords and a steady, unobtrusive drum machine beat. A round synth bass provides a warm low end. The lead male vocal is clear and emotive, delivered in a smooth tenor with occasional falsetto ad-libs and layered harmonies that swell during the anthemic chorus.", "lyrics": "[Intro]\nYeah\nOh\nYeah\n\n[Verse 1]\nMidnight whispers in my ear\nStars above, they're shining clear\nCity lights, they start to fade\nUnderneath, our plans we've made\n\n[Chorus]\nYou're my heartbeat symphony\nEchoes of sweet destiny\nEvery beat a symphony\nYou and me, we're wild and free", "instrumental": false, "duration": 10, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "en", "bpm": 100, "keyscale": "A major", "timesignature": "4", "seed": 1234, "inference_steps": 8, "guidance_scale": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": false, "lm_temperature": 0.0, "lm_top_k": 0, "lm_top_p": 1.0 } ] }, "reference_text2music_example_01_600s_then_160s_temp0": { "requests": [ { "task_type": "text2music", "caption": "An explosive, high-energy pop-rock track with a strong anime theme song feel. The song kicks off with a catchy, synthesized brass fanfare over a driving rock beat with punchy drums and a solid bassline. A powerful, clear male vocal enters with a theatrical and energetic delivery, soaring through the verses and hitting powerful high notes in the chorus. The arrangement is dense and dynamic, featuring rhythmic electric guitar chords, brief instrumental breaks with synth flourishes, and a consistent, danceable groove throughout. The overall mood is triumphant, adventurous, and exhilarating.", "lyrics": "[Intro - Synth Brass Fanfare]\n\n[Verse 1]\n黑夜里的风吹过耳畔\n甜蜜时光转瞬即万\n脚步飘摇在星光上\n心追节奏心跳狂乱\n耳边传来电吉他呼唤\n手指轻触碰点流点燃\n梦在云端任它蔓延\n疯狂跳跃自由无间\n\n[Chorus]\n心电感应在震动间\n拥抱未来勇敢冒险\n那旋律在心中无限\n世界变得如此耀眼\n\n[Instrumental Break - Synth Brass Melody]\n\n[Verse 2]\n鼓点撞击黑夜的底端\n跳动节拍连接你我俩\n在这里让灵魂发光\n燃尽所有不留遗憾\n\n[Instrumental Break - Synth Brass Melody]\n\n[Bridge]\n光影交错彼此的视线\n霓虹之下夜空的蔚蓝\n月光洒下温热心田\n追逐梦想它不会遥远\n\n[Chorus]\n心电感应在震动间\n拥抱未来勇敢冒险\n那旋律在心中无限\n世界变得如此耀眼\n\n[Outro - Instrumental with Synth Brass Melody]\n[Song ends abruptly]", "instrumental": false, "duration": 600, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "zh", "bpm": 100, "keyscale": "B minor", "timesignature": "4", "seed": 1234, "inference_steps": 8, "guidance_scale": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": true, "dcw_mode": "double", "dcw_scaler": 0.05, "dcw_high_scaler": 0.02, "dcw_wavelet": "haar", "lm_temperature": 0.0, "lm_cfg_scale": 2.0, "lm_top_k": 0, "lm_top_p": 1.0 }, { "task_type": "text2music", "caption": "An explosive, high-energy pop-rock track with a strong anime theme song feel. The song kicks off with a catchy, synthesized brass fanfare over a driving rock beat with punchy drums and a solid bassline. A powerful, clear male vocal enters with a theatrical and energetic delivery, soaring through the verses and hitting powerful high notes in the chorus. The arrangement is dense and dynamic, featuring rhythmic electric guitar chords, brief instrumental breaks with synth flourishes, and a consistent, danceable groove throughout. The overall mood is triumphant, adventurous, and exhilarating.", "lyrics": "[Intro - Synth Brass Fanfare]\n\n[Verse 1]\n黑夜里的风吹过耳畔\n甜蜜时光转瞬即万\n脚步飘摇在星光上\n心追节奏心跳狂乱\n耳边传来电吉他呼唤\n手指轻触碰点流点燃\n梦在云端任它蔓延\n疯狂跳跃自由无间\n\n[Chorus]\n心电感应在震动间\n拥抱未来勇敢冒险\n那旋律在心中无限\n世界变得如此耀眼\n\n[Instrumental Break - Synth Brass Melody]\n\n[Verse 2]\n鼓点撞击黑夜的底端\n跳动节拍连接你我俩\n在这里让灵魂发光\n燃尽所有不留遗憾\n\n[Instrumental Break - Synth Brass Melody]\n\n[Bridge]\n光影交错彼此的视线\n霓虹之下夜空的蔚蓝\n月光洒下温热心田\n追逐梦想它不会遥远\n\n[Chorus]\n心电感应在震动间\n拥抱未来勇敢冒险\n那旋律在心中无限\n世界变得如此耀眼\n\n[Outro - Instrumental with Synth Brass Melody]\n[Song ends abruptly]", "instrumental": false, "duration": 160, "thinking": true, "use_cot_metas": true, "use_cot_caption": true, "use_cot_language": true, "vocal_language": "zh", "bpm": 100, "keyscale": "B minor", "timesignature": "4", "seed": 1234, "inference_steps": 8, "guidance_scale": 1.0, "shift": 1.0, "infer_method": "ode", "audio_cover_strength": 1.0, "cover_noise_strength": 0.0, "sampler_mode": "euler", "velocity_norm_threshold": 0.0, "velocity_ema_factor": 0.0, "dcw_enabled": true, "dcw_mode": "double", "dcw_scaler": 0.05, "dcw_high_scaler": 0.02, "dcw_wavelet": "haar", "lm_temperature": 0.0, "lm_cfg_scale": 2.0, "lm_top_k": 0, "lm_top_p": 0.9 } ] } }