GPT Image 2 is LIVE Now. Try in Image Generator→
登錄
首頁/探索/OpenAI Models/openai/gpt-image-2/edit

OpenAI GPT Image 2 Edit

openai /

OpenAI's GPT Image 2 Edit enables image editing from natural-language instructions with one or more reference images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-image
Input

Drag & drop or click to upload

If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Idle

您的請求將花費 $0.1 每次運行。

使用 $1 您可以運行此模型大約 10 次。

還有一件事：

示例查看全部

A high-end fashion editorial portrait of a blonde Western female model wearing the earrings shown in the image. The model is in her early 20s, with flawless, radiant skin and subtle freckles. She wears natural, dewy makeup with a soft blush and nude glossy lips. Her features are refined, with high cheekbones and a well-defined jawline. Her blonde hair is styled in a sleek low bun, neatly tucked behind her ears to fully showcase the earrings. She is posed in an elegant side profile, with her eyes gently closed, conveying a calm, graceful, and serene expression. The lighting is warm natural light, with soft botanical shadows cast across her face and shoulders, creating a soft yet high-contrast editorial atmosphere. The light enhances the texture of her skin as well as the reflective shine of the gold and pearl. The background is minimal, in warm beige tones, softly blurred, presenting a premium lifestyle aesthetic. Shot in an ultra-realistic style with fashion magazine quality, using an 85mm lens and shallow depth of field. The earrings are in sharp focus, with soft cinematic lighting, high detail, and a luxurious jewelry advertisement style, in 8K resolution.

README

OpenAI GPT Image 2 Edit

GPT Image 2 Edit is OpenAI's AI-powered image editing model that transforms reference images based on natural-language instructions.

Parameters

ParameterRequiredDescription
imagesYesReference images to edit
promptYesText description of the desired edit
aspect_ratioNoAspect ratio: 1:1 (default), 2:3, 3:2

How to Use

  1. Upload reference images — add the images you want to edit.
  2. Write your prompt — describe the edit clearly.
  3. Choose aspect ratio (optional) — 1:1 (default), 2:3, or 3:2.
  4. Run — submit and download your edited image.

Notes

  • Both images and prompt are required fields.
  • Supported aspect ratios: 1:1, 2:3, 3:2.