The interface is localized. Skill descriptions and documents are machine-translated by AI into your language; code, commands, paths and technical terms stay in the original, and the author's document governs.
Explore skills
Productivity · SKILL.md

runway-gen4-image

runway-gen4-image

Runway | Gen4 | Image. Generate images from text prompts using Runway Gen4. AI image generation with reference image support and multiple aspect ratios. Triggers: runway gen4 image, runway image, gen4 image, runway generate image, ai image generation runway

Independent GitHub snapshot · Automated classification · Original documentation governs

Skill documentation

GitHub

name: runway-gen4-image description: "Runway | Gen4 | Image. Generate images from text prompts using Runway Gen4. AI image generation with reference image support and multiple aspect ratios. Triggers: runway gen4 image, runway image, gen4 image, runway generate image, ai image generation runway" allowed-tools: Bash(curl *), WebFetch

Runway | Gen4 | Image

Generate images from text prompts using Runway Gen4. Supports up to 3 reference images for style and content guidance, with a wide range of aspect ratios and public figure moderation controls.

Quick Start

Requires an each::labs API key. Get one at eachlabs.ai.

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "runway-gen4-image",
    "version": "0.0.1",
    "input": {
      "prompt": "A mystical underwater temple with bioluminescent coral and ancient stone pillars",
      "aspect_ratio": "1920:1080"
    }
  }'

Parameters

ParameterTypeDefaultDescription
aspect_ratiostring1024:1024Output dimensions. Options: 1920:1080, 1080:1920, 1024:1024, 1360:768, 1080:1080, 1168:880, 1440:1080, 1080:1440, 1808:768, 2112:912, 1280:720, 720:1280, 720:720, 960:720, 720:960, 1680:720
promptstring-Text prompt for image generation
public_figure_moderationstringautoPublic figure handling. Options: auto, low
reference_image_1string-First reference image URL
reference_image_2string-Second reference image URL
reference_image_3string-Third reference image URL
seedinteger-Random seed for reproducible results

Examples

Widescreen landscape:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "runway-gen4-image",
    "version": "0.0.1",
    "input": {
      "prompt": "A vast alien desert with twin suns setting, purple and orange sky, crystalline rock formations",
      "aspect_ratio": "1920:1080",
      "seed": 42
    }
  }'

Image with reference style:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "runway-gen4-image",
    "version": "0.0.1",
    "input": {
      "prompt": "A cozy coffee shop interior in the same style as the reference",
      "reference_image_1": "https://example.com/style-reference.jpg",
      "aspect_ratio": "1360:768"
    }
  }'

Related Models

Documentation

Saved skills