🎼 ACE Step — Pro Pack on RunComfy — 🎼 ACE Step — Pro Pack on 运行Comfy

🎼 ACE Step — Pro Pack on 运行Comfy

Tag-driven music generation, inpAInting, and outpAInting with StepFun-AI's ACE Step open-weights 模型. Four 命令行工具-reachable 端点s, $0.0002–0.0003 per second of audio, up to 4 minutes per call.

运行comfy.com · ACE Step base · ACE Step 1.5 · 命令行工具 docs

Powered by the 运行Comfy 命令行工具 # 1. 安装 (one of — see 运行comfy-命令行工具 技能 for detAIls) npm i -g @运行comfy/命令行工具 # global 安装 npx -y @运行comfy/命令行工具 --version # zero-安装

# 2. 签名 in 运行comfy 记录in # or in CI: 导出 运行COMFY_令牌=<令牌>

# 3. 生成 运行comfy 运行 acestep-AI/ace-step/text-to-audio \ --输入 '{"tags": "..."}' \ --输出-dir ./out

命令行工具 deep dive: 运行comfy-命令行工具 技能.

Pick the right 端点

列出ed newest first.

ACE Step 1.5 (text-to-audio) — acestep-AI/ace-step-1.5/text-to-audio

Latest ACE Step generation. 50+ language vocal support, refined structured-lyric handling, otherwise same shape as base. Slightly higher cost ($0.0003/s vs $0.0002/s). Pick for: multilingual lyrics, hero-质量 vocal 追踪s, vocal songs that need 清理 section structure. Avoid for: cost-sensitive batches where the base 模型 is good enough.

ACE Step (text-to-audio) — acestep-AI/ace-step/text-to-audio (default — cheap & fast)

Original ACE Step. Tag-driven composition, optional lyrics, 5–240 s stereo. $0.0002/s — ~27× cheaper than ElevenLabs Music. Pick for: high-volume drafts, background music, jingles, game loops, cost-sensitive iteration. Avoid for: maximally polished commercial vocal hooks — try ACE Step 1.5 or ElevenLabs Music for those.

ACE Step (audio-inpAInt) — acestep-AI/ace-step/audio-inpAInt

Re生成 a time range inside an existing 追踪 (not mask-based; uses 启动_time / end_time in seconds, each anchored to 追踪 启动 or end). Pick for: fix a bad chorus in the middle, swap the bridge, replace a 20 s section without re-rendering the whole song. Avoid for: edits that aren't time-bounded — those don't fit the 模式.

ACE Step (audio-outpAInt) — acestep-AI/ace-step/audio-outpAInt

Extend an existing 追踪 bidirectionally — 添加 intro before, outro after, or 机器人h. Pick for: lengthening a 30 s draft into a 2 min cut, 添加ing a fade-in, building a longer arrangement around an existing hook. Avoid for: extending a 追踪 past 4 min total — chAIn calls instead.

路由 1: ACE Step text-to-audio (default)

模型: acestep-AI/ace-step/text-to-audio (or acestep-AI/ace-step-1.5/text-to-audio for the 1.5 variant)

模式 (机器人h variants — same shape) Field Type Required Default Notes tags string yes — Comma-separated genre / mood / instrument tags. Drives composition lyrics string no — Vocal content. Use section markers [Verse], [Chorus], [Bridge]. Use [inst] or [instrumental] for no vocals duration int no 60 Audio length in seconds. 5–240 (max 4 min per call) 种子 int no -1 Reproducibility; -1 randomizes

Pricing: ACE Step $0.0002/s · ACE Step 1.5 $0.0003/s. 60 s ≈ $0.012 / $0.018; 240 s ≈ $0.048 / $0.072.

Invoke

Tag-driven instrumental:

运行comfy 运行 acestep-AI/ace-step/text-to-audio \ --输入 '{ "tags": "lo-fi hip-hop, mellow, vinyl crackle, rhodes piano, soft drums, 75 BPM", "lyrics": "[inst]", "duration": 90 }' \ --输出-dir ./out

Full vocal song with structure (use 1.5 for multilingual):

运行comfy 运行 acestep-AI/ace-step-1.5/text-to-audio \ --输入 '{ "tags": "indie pop, anthemic, electric 图形界面tar, driving drums, female vocal, 120 BPM", "lyrics": "[Verse]\nChalk on the palms, laces double-knotted\nMorning on the ridge, the sun is rising\n[Chorus]\nWe rise, we strike, we never fade out\nWe rise, we strike, we sing it loud\n[Bridge]\nSoft piano breakdown\n[Outro]\nFull band, fade", "duration": 60 }' \ --输出-dir ./out

Prompting tips Tags do the heavy lifting — be specific: "lo-fi hip-hop, mellow, vinyl crackle, rhodes piano, soft drums, 75 BPM" beats "chill music". Include BPM in tags when it matters — ACE respects tempo language. Lyrics with section markers: [Verse], [Chorus], [Bridge], [Outro]. Keep meter consistent across lines. Instrumental shortcut: "lyrics": "[inst]" or "[instrumental]". Belt-and-suspenders: also say "no vocals" in tags. Multilingual vocals: ACE Step 1.5 covers 50+ languages. Write lyrics directly in the tar获取 language; tag the language too ("japanese vocal, j-pop"). Fix the 种子 for reproducibility ("种子": 42); use -1 to explore variations. Cheap draft → polish: ACE Step at 5–10× lower cost is great for iterating tags before committing to a long render. 路由 2: ACE Step audio-inpAInt

模型: acestep-AI/ace-step/audio-inpAInt Cata记录: audio-inpAInt

模式 Field Type Required Default Notes audio string yes — HTTPS URL to MP3 / WAV / FLAC. Up to 60 min tags string yes — Comma-separated tags steering the re生成d segment 启动_time float no — 启动 of editable segment, in seconds (0–240) 启动_time_relative_to enum no 启动 启动 or end — anchor for 启动_time e