UI はローカライズ済みです。スキルの紹介と説明文書は選択した言語へ AI が自動翻訳し、コード・コマンド・パス・専門用語は原文のままです。原作者の文書が優先されます。
スキルを探す
生産性・共同作業 · SKILL.md

gpt-image-v1-5-edit

gpt-image-v1-5-edit

GPT Image | v1.5 | Edit. Edit images using GPT Image v1.5 with reference images and text prompts. Triggers: gpt image edit, image editing, ai edit, openai image

Independent GitHub snapshot · Automated classification · Original documentation governs

スキルの説明

GitHub

name: gpt-image-v1-5-edit description: "GPT Image | v1.5 | Edit. Edit images using GPT Image v1.5 with reference images and text prompts. Triggers: gpt image edit, image editing, ai edit, openai image" allowed-tools: Bash(curl *), WebFetch

GPT Image | v1.5 | Edit

Edit images using GPT Image v1.5. Supports reference images, transparent backgrounds, configurable moderation levels, and quality settings. Can generate multiple output images in various formats.

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": "gpt-image-v1-5-edit",
    "version": "0.0.1",
    "input": {
      "prompt": "Add a festive holiday wreath on the front door",
      "image_urls": ["https://example.com/house-front.jpg"],
      "image_size": "1024x1024",
      "quality": "high",
      "output_format": "png"
    }
  }'

Parameters

ParameterTypeDefaultDescription
backgroundstringautoBackground for the generated image. Options: auto, transparent, opaque
image_sizestring1024x1024Aspect ratio for the generated image. Options: 1024x1024, 1536x1024, 1024x1536
image_urlsarray-The URLs of the images to use as a reference for the generation.
input_fidelitystringhighInput fidelity for the generated image. Options: low, high
moderationstringlowContent moderation level. Options: low, auto
num_imagesinteger1Number of images to generate.
output_formatstringpngOutput format for the images. Options: jpeg, png, webp
promptstring-The prompt for image generation.
qualitystringhighQuality for the generated image. Options: low, medium, high

Examples

Simple edit:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "gpt-image-v1-5-edit",
    "version": "0.0.1",
    "input": {
      "prompt": "Change the wall paint to a soft blue color",
      "image_urls": ["https://example.com/living-room.jpg"]
    }
  }'

Transparent background edit:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "gpt-image-v1-5-edit",
    "version": "0.0.1",
    "input": {
      "prompt": "Extract the product and place it on a clean transparent background",
      "image_urls": ["https://example.com/product-messy-bg.jpg"],
      "background": "transparent",
      "image_size": "1024x1024",
      "quality": "high",
      "num_images": 2,
      "output_format": "png"
    }
  }'

Related Models

Documentation

保存したスキル