SkillsAdd

runwayml/skills

rw-generate-image

Generate images directly using the Runway API via runnable scripts. Supports text-to-image with optional reference images.

First seen Apr 16, 2026

Installation

$ npx skills add runwayml/skills --skill rw-generate-image
View on skills.sh ↗ GitHub repository ↗

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

recipe-generate-report-from-sheet Similar name
googleworkspace/cli

Read data from a Google Sheet and create a formatted Google Docs report.

27.5K installs
playwright-generate-test Similar name
github/awesome-copilot

Generate a Playwright test based on a scenario using Playwright MCP

18K installs
generate-custom-instructions-from-codebase Similar name
github/awesome-copilot

Migration and code evolution instructions generator for GitHub Copilot. Analyzes differences be…

9K installs
comment-code-generate-a-tutorial Similar name
github/awesome-copilot

Transform this Python script into a polished, beginner-friendly project by refactoring the code…

8.9K installs
structured-autonomy-generate Similar name
github/awesome-copilot

Structured Autonomy Implementation Generator Prompt

8.8K installs
stitch::generate-design Similar name
google-labs-code/stitch-skills

Generate new screens from text prompts or images, edit existing screens with prompts and design…

8.1K installs

Also in this package

Other skills from runwayml/skills · top by installs.

npx skills add runwayml/skills
rw-generate-video 495 use-runway-api 288 rw-api-reference 262 rw-check-org-details 248 rw-integrate-uploads 247 rw-integrate-video 241 rw-setup-api-key 240 rw-generate-audio 238 rw-fetch-api-reference 230 rw-integrate-image 225

Browse all from runwayml/skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 68
License LICENSE
Default branch main
Open issues 12
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

Allowed toolsRead, Grep, Glob, Edit, Write, Bash(uv run *), Bash(command -v uv)
Declared agents gemini

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 4,038 B
  • docs SUMMARY.md 147 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 246 installs

SKILL.md

Generate Image

Generate images 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_image.py --prompt "your description" --filename "output.png" [--model gen4_image] [--ratio 1280:720] [--reference-images Tag=URL ...]

Preflight

  1. command -v uv must succeed
  2. RUNWAYMLAPISECRET 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

  • --reference-images Tag=URL fetches arbitrary remote images 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 references influence the result.

Available Models

Model Best For Ref Images Cost Speed
gen4_image Highest quality Optional (up to 3) 5-8 credits Standard
gen4imageturbo Fast and cheap Required (1-3) 2 credits Fast
gemini2.5flash Google Gemini Optional (up to 3) 5 credits Standard

Model Selection Guidance

  • "fast", "cheap", "draft" -> gemini2.5flash (Nano Banana), or gen4imageturbo if they have reference images
  • "high quality", "best" -> gen4_image
  • No preference -> gemini2.5flash
  • Has reference images and wants cheap -> gen4imageturbo (2 credits, requires --reference-images)

Parameters

Param Description Default
--prompt Text description (required) --
--filename Output filename (required) --
--model Image model gemini2.5flash
--ratio Aspect ratio. gemini2.5flash: 1344:768, 768:1344, 1024:1024, etc. gen4_image: 1280:720, 1360:768, 1920:1080, etc. Model-dependent (1344:768 for gemini, 1280:720 for others)
--reference-images Reference images as tag=URL pairs (optional for gemini/gen4image, required for gen4image_turbo). Tag: lowercase, 3-16 chars, e.g. product=URL --
--output-dir Output directory cwd

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

Filename Convention

Pattern: yyyy-mm-dd-hh-mm-ss-name.png

Examples

Basic image:

uv run scripts/generate_image.py --prompt "A serene Japanese garden with cherry blossoms" --filename "2026-04-14-japanese-garden.png"

With a local reference image (gen4_image):

uv run scripts/generate_image.py --prompt "@product on a marble counter, lifestyle photo" --model gen4_image --reference-images product=./product.jpg --filename "2026-04-14-product-lifestyle.png"

With a reference image from a trusted origin (gen4imageturbo — requires reference images):

uv run scripts/generate_image.py --prompt "A neon sign reading SALE in @style" --model gen4_image_turbo --reference-images style=https://cdn.yourapp.com/style.jpg --filename "draft.png"

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 image file back -- just inform the user of the saved path

Common Failures

  • Error: No API key -> set RUNWAYMLAPISECRET in the environment (e.g. export RUNWAYMLAPISECRET=... or a .env file).
  • Error: Task failed -- SAFETY.INPUT.* -> content moderation, suggest different prompt
  • API error 429 -> rate limited, script auto-retries