Video Extend

Takes an existing video clip and generates more frames that continue it, using Google Veo 3-1's extend endpoints via the RunComfy CLI. Useful when you hit the per-call duration cap on a generated clip or when you want to build a narrative shot by shot without re-generating from scratch. The full endpoint maintains identity and lighting consistency across extends; the fast variant trades quality for iteration speed. Prompting works best when you describe only the next beat rather than re-describing the entire scene, and you anchor the camera explicitly to avoid drift. Chain consecutive extends for longer sequences, though identity coherence degrades after three or four generations.

skills.sh installs: 273.8K
GitHub stars: 16
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add runcomfy-com/skills --skill video-extend --agent claude-code

Installs into .claude/skills of the current project.

Files

Video Extend

Continue an existing video clip past its per-call duration cap, or chain a narrative shot-by-shot from a single seed. This skill routes to Google Veo 3-1's extend-video endpoints and ships the documented prompting patterns + the exact runcomfy run invoke.

runcomfy.com · Veo 3-1 extend-video · CLI docs

Powered by the RunComfy CLI

# 1. Install (see runcomfy-cli skill for details)
npm i -g @runcomfy/cli      # or:  npx -y @runcomfy/cli --version

# 2. Sign in
runcomfy login              # or in CI: export RUNCOMFY_TOKEN=<token>

# 3. Extend
runcomfy run google-deepmind/veo-3-1/extend-video \
  --input '{"video_url": "https://...", "prompt": "..."}' \
  --output-dir ./out

CLI deep dive: runcomfy-cli skill.