ace-step
๐ฏSkillfrom prime-skills/runcomfy-agent-skills
Installation
npx vibeindex add prime-skills/runcomfy-agent-skills --skill ace-stepnpx skills add prime-skills/runcomfy-agent-skills --skill ace-step~/.claude/skills/ace-step/SKILL.md
|A Claude Code skill for tag-driven music generation, inpainting, and outpainting with StepFun-AI's open-weights ACE Step on RunComfy, offering 4 endpoints at $0.0002-0.0003/s with Apache 2.0 licensing and 50+ language vocal support.
Overview
ACE Step is a Claude Code skill that provides tag-driven music composition on RunComfy using StepFun-AI's open-weights ACE Step model. It offers four endpoints via the runcomfy CLI: full generation (create complete tracks from tags and lyrics), inpainting (replace a time range within an existing track), outpainting (extend a track before or after its current boundaries), and retag (change genre/mood tags while preserving the audio). All endpoints run at $0.0002 to $0.0003 per second under Apache 2.0 licensing. ACE Step 1.5 supports vocals in 50+ languages.
Key Features
- Tag-driven composition: Control genre, mood, instrumentation, tempo, and vocal style through structured tags rather than free-form prompts (e.g.,
pop rock, male vocals, 120bpm, electric guitar) - Four endpoints: Generate full tracks, inpaint sections, outpaint extensions, and retag existing audio without re-generation
- Open-weights model: Apache 2.0 licensed, allowing commercial use without per-track royalties or licensing fees
- Cost-effective: $0.0002 to $0.0003 per second of generated audio, enabling high-volume production workflows
- Multilingual vocals: ACE Step 1.5 generates vocals in 50+ languages including English, Korean, Japanese, Chinese, and Spanish
- Anchor-relative editing: Inpainting and outpainting use anchor timestamps to precisely target edit regions within the timeline
Who is this for?
- Indie musicians who want to prototype song ideas quickly with tag-based control over genre, tempo, and instrumentation
- Content creators needing royalty-free background music at minimal cost for videos, podcasts, or streams
- Pipeline developers building automated music generation workflows that need a cost-effective, API-accessible model
- Podcast producers who want to generate custom intro/outro music or extend existing tracks to match episode length
Same repository
prime-skills/runcomfy-agent-skills(25 items)
SKILL.md
More from this repository10
A smart intent-routing skill for video editing on RunComfy that automatically selects the best model (Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, or Lucy Edit Restyle) based on what the user wants to do, from general restyling and background swaps to precise motion transfer and outfit changes.
A smart intent-routing skill that animates still images on RunComfy by selecting the optimal model: HappyHorse 1.0 I2V for general portrait and product animation with native audio, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition with image, video, and audio references.
A skill for generating images with Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family on RunComfy, optimized for rapid iteration, batch ideation, in-image typography rendering, and optional web-grounded context with support for resolutions from 0.5K to 4K.
A smart intent-routing skill for image editing on RunComfy that selects the optimal model from Nano Banana Edit (batch up to 20 images), GPT Image 2 Edit (multilingual text rewrite, multi-ref composition), Flux Kontext Pro (single-shot precise local edit), or Z-Image Turbo Inpaint (mask-driven region edit) based on user intent.
A Claude Code skill that enables precise single-image editing using Black Forest Labs's Flux 1 Kontext Pro model through the RunComfy CLI, with built-in prompting patterns for high-fidelity local edits.
A skill for generating text-to-video with Wan 2.7, Wan-AI's flagship motion model on RunComfy, featuring multi-reference conditioning, audio-driven lip-sync via custom audio tracks, smooth transition physics, prompt expansion control, and up to 1080p output at 15 seconds duration.
A Claude Code skill for generating text-to-video clips with HappyHorse 1.0 via the RunComfy CLI. HappyHorse 1.0 is currently ranked #1 on the Artificial Analysis Video Arena, producing native 1080p video with in-pass synchronized audio and multi-shot character consistency.
A Claude Code skill for generating video with Kling 3.0 via the RunComfy CLI. Covers all six Kling 3.0 endpoints across three rendering tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video), with native synchronized audio and multi-shot character consistency.
A Claude Code skill that generates custom OpenAI Codex Pets from a single reference image via the RunComfy CLI. It produces a Codex-compatible spritesheet (1536x1872, 8 columns x 9 rows) and pet.json manifest using GPT Image 2 and ImageMagick, without requiring Codex Pro or an OPENAI_API_KEY.
A Claude Code skill that acts as a smart router for AI video generation across the full RunComfy model catalog. Supports text-to-video, image-to-video, and video-extend modes with models including HappyHorse 1.0, Kling 3.0, Wan 2.7, Seedance, Veo 3.1, and more.