{ "_comment": "songforge 唯一事实来源。改这里,不要改脚本里的硬编码常量。", "engine": { "server": "http://127.0.0.1:8188", "timeout_sec": 3600, "poll_interval_sec": 10, "submit_retries": 3 }, "model": { "checkpoint": "ace_step_1.5_turbo_swl_fused.safetensors", "lora": "swl_voice_best_ep257.safetensors", "lora_model_strength": 0.5, "lora_clip_strength": 0.5, "denied_checkpoints": [ "yue2_3b_int8_convrot.safetensors", "ace_step_1.5_turbo_aio.safetensors" ] }, "sampler": { "shift": 5.5, "sampling": "flow", "steps": 28, "cfg": 2.0, "sampler_name": "euler", "scheduler": "simple", "denoise": 1.0 }, "encode": { "cfg_scale": 3.0, "temperature": 0.68, "top_p": 0.88, "top_k": 50, "min_p": 0.02, "generate_audio_codes": true, "timesignature": "4" }, "paths": { "_comment": "相对路径均相对 user/default/workflows。本机绝对路径放 local.json(gitignore)。音频在 ComfyUI/output//。过程物按日落在 data/runs|tmp/YYYY-MM-DD/。", "workflow_template": "urbanhiphop-身体先听懂.json", "runs_dir": "songforge/data/runs", "tmp_dir": "songforge/data/tmp", "lyrics_dir": "songforge/input/lyrics", "qc_cache_dir": "songforge/cache/qc", "style_cache_dir": "songforge/cache/style", "index_dir": "songforge/index", "catalog_file": "songforge/index/catalog.jsonl", "baseline_dir": "songforge/config/baseline", "comfy_root": null, "qc_python": null, "music_dir": null, "output_prefix": "MyMusic", "output_format": "flac" }, "song": { "language": "zh", "time_signature": "4", "duration_range": [150, 200], "_duration_extra_comment": "duration_extra_ranges 供短视频/口水歌等场景显式放行短时长,不削弱主区间。主区间是 35 首已验证实歌的经验范围,短时长没有对应实歌背书,所以必须显式列出而不是直接放宽。", "duration_extra_ranges": [[100, 130]] }, "lyrics": { "_comment": "死心塌地时长对应关系。阈值由 8 首已验证可生成的歌实测反推,不是理论值;改前先跑 selftest 实歌回归。", "_calibrated_on": "remake_v5.py 的 8 首实歌:每可唱小节 4.56~7.64 音节(均值 6.17),每句 5.9~7.4 音节(均值 6.7)", "sing_bar_ratio": 0.70, "intro_bars": 8, "syllable_per_bar_min": 4.40, "syllable_per_bar_max": 7.80, "line_syllable_max": 12, "ideal_line_syllable": [5, 12], "_profile_comment": "密度档。default = 人声填满整首(中文说唱/流行)。sparse = 音乐主导、人声点缀(英文低声吟唱/纯器乐周边)。", "_profile_why": "default 档是按 8 首'人声填满全曲'的实歌反推的。直接拿它校验第三张那种'音乐当主角、人声只是点缀'的写法,会把只有几句 ooh ooh 的低音吟唱判成歌词过少,逼着写满 254 音节以上——结果就是'只有人声没有音乐',正好和目标相反。所以稀疏写法必须用另一套阈值,不能共用。", "profiles": { "sparse": { "_comment": "稀疏档:可唱小节只占 25%(其余留给器乐),句子下限放宽到 3 音节,允许 ooh ooh / mmm 这类短语气词。", "sing_bar_ratio": 0.25, "syllable_per_bar_min": 4.40, "syllable_per_bar_max": 7.80, "line_syllable_max": 12, "ideal_line_syllable": [3, 12] } } }, "rules": { "trigger_word": "swlvoice", "intro_bars": 8 } }