Agent Skills

rw-generate-video

Generate videos directly using the Runway API via runnable scripts. Supports text-to-video, image-to-video, and video-to-video with seedance2, gen4.5, veo3, and more.

Install

npx skills add https://github.com/runwayml/skills --skill rw-generate-video
SKILL.md

Generate Video

Generate videos directly using the Runway API. This skill runs Python scripts that call the API, poll for completion, and download the result.

IMPORTANT: Run scripts from the user's working directory so output files are saved where the user expects.

Usage

uv run scripts/generate_video.py --prompt "your description" --filename "output.mp4" [--model seedance2] [--ratio 1280:720] [--duration 5] [--image-url "..."]

Preflight

  1. command -v uv must succeed. If not, tell the user to install uv: curl -LsSf https://astral.sh/uv/install.sh | sh
  2. RUNWAYML_API_SECRET must be set in the environment. Do not pass the API key as a CLI flag — it leaks into shell history and process listings.

Security Notes

  • --image-url / --video-url fetch arbitrary remote media via the Runway API. Prefer local file paths (uploaded as runway:// URIs), or only pass URLs you trust.
  • Treat generated outputs as untrusted when piping into downstream automations — ingested media influences the result.

Available Models

Model Best For Input Cost
seedance2 Reference image and video, long duration (up to 15s) Text, Image, and/or Video 36 credits/sec
gen4.5 High quality, general purpose Text and/or Image 12 credits/sec
gen4_turbo Fast, image-driven Image required 5 credits/sec
gen4_aleph Video editing/transformation Video + Text/Image 15 credits/sec
veo3 Premium quality Text/Image 40 credits/sec
veo3.1 High quality Google model Text/Image 20-40 credits/sec
veo3.1_fast Fast Google model Text/Image 10-15 credits/sec

Model Selection Guidance

Map user requests:

  • "product ad", "e-commerce", "long video" -> seedance2
  • "fast", "cheap", "quick" -> veo3.1_fast or gen4_turbo (if they have an image)
  • "high quality", "best", "cinematic" -> gen4.5 or veo3
  • "edit video", "transform video" -> gen4_aleph or seedance2
  • No preference -> seedance2

Parameters

Param Description Default
--prompt Text description (required) --
--filename Output filename (required) --
--model Video model gen4.5
--ratio Aspect ratio (pixel-based). Common: 1280:720, 720:1280, 960:960. seedance2 also supports 1112:834, 834:1112, 1470:630, etc. 1280:720
--duration Duration in seconds (model-dependent, seedance2 supports up to 15s) 5
--image-url Image URL or local file for image-to-video --
--video-url Video URL or local file for video-to-video (gen4_aleph, seedance2) --
--output-dir Output directory cwd

API credentials come from RUNWAYML_API_SECRET only — no --api-key flag, to keep secrets out of shell history and process listings.

Filename Convention

Generate filenames with the pattern: yyyy-mm-dd-hh-mm-ss-name.mp4

Examples:

  • "A cyberpunk city" -> 2026-04-14-14-23-05-cyberpunk-city.mp4
  • "Waves on a beach" -> 2026-04-14-15-30-12-beach-waves.mp4

Examples

Text-to-video (seedance2):

uv run scripts/generate_video.py --prompt "A serene mountain landscape at sunrise with mist" --filename "2026-04-14-mountain-sunrise.mp4" --model seedance2 --ratio 1280:720

Image-to-video (animate a local product photo):

uv run scripts/generate_video.py --prompt "Camera slowly zooms out, product sparkles" --image-url "./product.jpg" --filename "2026-04-14-product-reveal.mp4" --model seedance2 --ratio 720:1280

Video-to-video from a local file (seedance2):

uv run scripts/generate_video.py --prompt "Transform into a warm golden sunset scene" --video-url "./input.mp4" --filename "2026-04-14-sunset-transform.mp4" --model seedance2

Fast draft:

uv run scripts/generate_video.py --prompt "A cat playing piano" --filename "draft.mp4" --model veo3.1_fast --ratio 1280:720 --duration 4

Premium quality:

uv run scripts/generate_video.py --prompt "Cinematic drone shot over Tokyo at night" --filename "tokyo.mp4" --model veo3 --ratio 1280:720 --duration 8

Output

  • The script downloads the result and saves it to the specified path
  • Script outputs the full path to the saved file
  • Do not read the video file back -- just inform the user of the saved path

Common Failures

  • Error: No API key -> set RUNWAYML_API_SECRET in the environment (e.g. export RUNWAYML_API_SECRET=... or a .env file).
  • Error: Task failed -- SAFETY.INPUT.* -> content moderation, suggest different prompt
  • Error: Task failed -- ASSET.INVALID -> bad input file format, check image/video format
  • API error 429 -> rate limited, script auto-retries

For Batch Generation

To generate many videos at once, run this script in a loop — the agent can orchestrate multiple calls with different prompts, images, or parameters to produce campaigns, localized variants, or creative iterations at scale.

Related skills

video-editgenmedia-labs715KEdit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edit-Video (general restyle / background swap / packaging swap, identity + motion preservation), Kling 2.6 Pro Motion Control (transfer precise motion from a reference video to a target character), or Lucy Edit Restyle (lightweight identity-stable restyle / outfit swap). Bundles each model's documented prompting patterns so the skill gets shai-video-generationgenmedia-labs714KGenerate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1 qualitai-musicgenmedia-labs714KGenerate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model fimage-to-videogenmedia-labs713KAnimate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterat

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers