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
Development · SKILL.md

gemini-3-pro-image-preview-edit

gemini-3-pro-image-preview-edit

Gemini 3 Pro | Image Edit. Edit images using Google Gemini with multiple resolution options. Triggers: image editing, gemini, google, photo edit

Independent GitHub snapshot · Automated classification · Original documentation governs

Skill documentation

GitHub

name: gemini-3-pro-image-preview-edit description: "Gemini 3 Pro | Image Edit. Edit images using Google Gemini with multiple resolution options. Triggers: image editing, gemini, google, photo edit" allowed-tools: Bash(curl *), WebFetch

Gemini 3 Pro | Image Edit

Edit images using Google's Gemini 3 Pro model. Supports multiple aspect ratios, resolution up to 4K, and batch generation.

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": "gemini-3-pro-image-preview-edit",
    "version": "0.0.1",
    "input": {
      "prompt": "make the sky more dramatic with storm clouds",
      "image_urls": ["https://example.com/landscape.jpg"],
      "aspect_ratio": "16:9",
      "resolution": "1K"
    }
  }'

Parameters

ParameterTypeDefaultDescription
aspect_ratiostring1:1The aspect ratio of the generated image. enum: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
image_urlsarrayThe URLs of the images for editing.
num_imagesinteger1The number of images to generate.
output_formatstringpngThe format of the generated image. enum: jpeg, png, webp
promptstringThe prompt for image editing.
resolutionstring1KThe resolution of the image to generate. enum: 1K, 2K, 4K

Examples

High-res background replacement:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "gemini-3-pro-image-preview-edit",
    "version": "0.0.1",
    "input": {
      "prompt": "replace the background with a modern art gallery, white walls",
      "image_urls": ["https://example.com/portrait.jpg"],
      "aspect_ratio": "3:4",
      "resolution": "2K",
      "output_format": "png"
    }
  }'

Batch style edits:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "gemini-3-pro-image-preview-edit",
    "version": "0.0.1",
    "input": {
      "prompt": "convert to pencil sketch style, detailed cross-hatching",
      "image_urls": ["https://example.com/photo.jpg"],
      "num_images": 3,
      "resolution": "1K"
    }
  }'

Related Models

Documentation

Saved skills