L’interface est localisée ; les présentations et documents des Skills sont traduits automatiquement par IA dans votre langue. Le code, les commandes, chemins et termes techniques restent en version originale, et le document de l’auteur fait foi.
Explorer les Skills
Développement · SKILL.md

gemini-3-pro-image-preview

gemini-3-pro-image-preview

Gemini 3 | Pro | Image Preview. Generate images from text using Google Gemini with up to 4K resolution. Triggers: text to image, gemini, google, image generation

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: gemini-3-pro-image-preview description: "Gemini 3 | Pro | Image Preview. Generate images from text using Google Gemini with up to 4K resolution. Triggers: text to image, gemini, google, image generation" allowed-tools: Bash(curl *), WebFetch

Gemini 3 | Pro | Image Preview

Generate images from text prompts 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",
    "version": "0.0.1",
    "input": {
      "prompt": "a cozy reading nook by a window on a rainy day, warm lighting",
      "aspect_ratio": "4:3",
      "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
num_imagesinteger1The number of images to generate.
output_formatstringpngThe format of the generated image. enum: jpeg, png, webp
promptstringThe text prompt to generate an image from.
resolutionstring1KThe resolution of the image to generate. enum: 1K, 2K, 4K

Examples

Ultra-wide cinematic shot:

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",
    "version": "0.0.1",
    "input": {
      "prompt": "epic sci-fi space station orbiting a gas giant, cinematic lighting",
      "aspect_ratio": "21:9",
      "resolution": "4K",
      "output_format": "png"
    }
  }'

Batch portrait generation:

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",
    "version": "0.0.1",
    "input": {
      "prompt": "watercolor portrait of an old fisherman, weathered face, kind eyes",
      "aspect_ratio": "3:4",
      "resolution": "2K",
      "num_images": 4,
      "output_format": "jpeg"
    }
  }'

Related Models

Documentation

Skills enregistrées