gpt-image

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

GPT-Image-2

Generate and edit images with OpenAI's GPT-Image-2 via inference.sh CLI.

通过inference.sh CLI使用OpenAI的GPT-Image-2生成和编辑图片。

Quick Start

快速开始

Requires inference.sh CLI (
belt
). Install instructions

bash

belt login

belt app run openai/gpt-image-2 --input '{"prompt": "a cat astronaut floating in space"}'

需要inference.sh CLI（
belt
）。安装说明

bash

belt login

belt app run openai/gpt-image-2 --input '{"prompt": "a cat astronaut floating in space"}'

Capabilities

功能特性

GPT-Image-2 supports text-to-image generation, image editing with reference images, and mask-based inpainting — all through a single model.

Feature	Description
Text-to-Image	Generate images from text prompts
Image Editing	Edit images using reference images
Inpainting	Mask-based editing of specific regions
Batch Generation	Generate up to 10 images at once
Multiple Formats	PNG, JPEG, WebP output
Flexible Resolution	Any size in 32px increments (256–4096)

GPT-Image-2支持文本生成图片、基于参考图的图片编辑以及基于蒙版的图像修复——所有功能都通过单一模型实现。

特性	描述
文本生成图片	通过文本提示生成图片
图片编辑	使用参考图编辑图片
图像修复	对特定区域进行基于蒙版的编辑
批量生成	一次最多生成10张图片
多种格式	输出PNG、JPEG、WebP格式
灵活分辨率	支持32像素增量的任意尺寸（256–4096）

Examples

示例

Text-to-Image

文本生成图片

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "professional product photo of sneakers on a white background, studio lighting",
  "quality": "high"
}'

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "professional product photo of sneakers on a white background, studio lighting",
  "quality": "high"
}'

Multiple Images

生成多张图片

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "minimalist logo design for a coffee shop",
  "n": 4,
  "quality": "medium"
}'

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "minimalist logo design for a coffee shop",
  "n": 4,
  "quality": "medium"
}'

Image Editing with Reference

基于参考图的图片编辑

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "change the background to a beach at sunset",
  "images": ["https://your-image.jpg"]
}'

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "change the background to a beach at sunset",
  "images": ["https://your-image.jpg"]
}'

Multi-Image Reference

多参考图编辑

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "combine these two characters into one scene",
  "images": ["https://character1.jpg", "https://character2.jpg"]
}'

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "combine these two characters into one scene",
  "images": ["https://character1.jpg", "https://character2.jpg"]
}'

Inpainting with Mask

基于蒙版的图像修复

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "replace with a red sports car",
  "images": ["https://street-scene.jpg"],
  "mask": "https://car-mask.png"
}'

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "replace with a red sports car",
  "images": ["https://street-scene.jpg"],
  "mask": "https://car-mask.png"
}'

Custom Resolution

自定义分辨率

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "wide cinematic landscape, mountains at golden hour",
  "width": 1920,
  "height": 1080,
  "quality": "high"
}'

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "wide cinematic landscape, mountains at golden hour",
  "width": 1920,
  "height": 1080,
  "quality": "high"
}'

Fast Drafts

快速草稿生成

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "quick concept sketch of a robot",
  "quality": "low"
}'

bash

belt app run openai/gpt-image-2 --input '{
  "prompt": "quick concept sketch of a robot",
  "quality": "low"
}'

Pricing

定价

Quality	~Price per Image
Low	$0.006
Medium	$0.024
High	$0.21

Larger resolutions cost more. See

belt app get openai/gpt-image-2

for full pricing details.

画质	单张图片约价
低	$0.006
中	$0.024
高	$0.21

分辨率越高，价格越贵。查看完整定价详情请执行

belt app get openai/gpt-image-2

。

Parameters

参数

Parameter	Type	Default	Description
`prompt`	string	required	Text prompt describing the image
`images`	array	-	Reference image(s) for editing
`mask`	string	-	Mask image for inpainting
`n`	integer	1	Number of images (1–10)
`quality`	string	-	low, medium, or high
`width`	integer	-	Output width (256–4096, multiples of 32)
`height`	integer	-	Output height (256–4096, multiples of 32)
`output_format`	string	png	png, jpeg, or webp
`output_compression`	integer	-	Compression level for jpeg/webp (0–100)

参数	类型	默认值	描述
`prompt`	字符串	必填	描述图片的文本提示
`images`	数组	-	用于编辑的参考图片
`mask`	字符串	-	用于图像修复的蒙版图片
`n`	整数	1	生成图片数量（1–10）
`quality`	字符串	-	low、medium或high
`width`	整数	-	输出宽度（256–4096，32的倍数）
`height`	整数	-	输出高度（256–4096，32的倍数）
`output_format`	字符串	png	png、jpeg或webp
`output_compression`	整数	-	jpeg/webp的压缩级别（0–100）

Related Skills

Full platform skill (all 250+ apps)

全平台技能（包含250+应用）

npx skills add inference-sh/skills@infsh-cli

All image generation models

所有图像生成模型

npx skills add inference-sh/skills@ai-image-generation

FLUX models

FLUX模型

npx skills add inference-sh/skills@flux-image

Pruna P-Image (fast & economical)

Pruna P-Image（快速且经济）

npx skills add inference-sh/skills@p-image


Browse all image apps: `belt app list --category image`

npx skills add inference-sh/skills@p-image


浏览所有图像应用：`belt app list --category image`

Documentation

文档

Running Apps - How to run apps via CLI
Streaming Results - Real-time progress updates

运行应用 - 如何通过CLI运行应用
流式结果 - 实时进度更新

gpt-image

Original

Translation

GPT-Image-2

GPT-Image-2

Quick Start

快速开始

Capabilities

功能特性

Examples

示例

Text-to-Image

文本生成图片

Multiple Images

生成多张图片

Image Editing with Reference

基于参考图的图片编辑

Multi-Image Reference

多参考图编辑

Inpainting with Mask

基于蒙版的图像修复

Custom Resolution

自定义分辨率

Fast Drafts

快速草稿生成

Pricing

定价

Parameters

参数

Related Skills

相关技能

Full platform skill (all 250+ apps)

全平台技能（包含250+应用）

All image generation models

所有图像生成模型

FLUX models

FLUX模型

Pruna P-Image (fast & economical)

Pruna P-Image（快速且经济）

Documentation

文档