name: runway-reference-architecture description: "Runway reference architecture \u2014 AI video generation and creative
\ AI platform.\nUse when working with Runway for video generation, image editing,
\ or creative AI.\nTrigger with phrases like "runway reference architecture",
\ "runway-reference-architecture", "AI video generation".\n" allowed-tools: Read, Write, Edit, Bash(pip:), Bash(npm:), Bash(curl:*), Grep version: 2.0.0 license: MIT author: Jeremy Longshore jeremy@intentsolutions.io tags:

• saas
• runway
• ai
• video-generation
• creative compatibility: Designed for Claude Code, also compatible with Codex and OpenClaw

Runway Reference Architecture

Overview

Implementation patterns for Runway reference architecture — AI video generation platform.

Prerequisites

• Completed runway-install-auth setup

Instructions

Step 1: SDK Pattern

from runwayml import RunwayML

client = RunwayML()

task = client.image_to_video.create(
    model='gen3a_turbo',
    prompt_text='A serene lake at dawn, mist rising, birds flying',
    duration=5,
)
result = task.wait_for_task_output()
if result.status == 'SUCCEEDED':
    print(f"Video: {result.output[0]}")

Output

• Runway integration for reference architecture

Error Handling

Resources

• Runway API Documentation
• Python SDK

Next Steps

See related Runway skills for more workflows.