GPT – image – 1 – The latest image generation model launched by OpenAI

What is GPT-image-1?

GPT-image-1 is a native multimodal image generation model launched by OpenAI, available to developers via API. The model generates high-quality, professional-grade images based on text prompts and input images, supporting a variety of styles and customization features such as image quality, size, format, and compression level. It is widely used across creative design, e-commerce, education, and marketing fields—for example, turning sketches into graphics, generating product displays, or creating brand visual assets. GPT-image-1 has already been adopted by major creative platforms including Adobe and Figma.

Key Features of GPT-image-1

• Text-to-Image Generation: Generate images based on text descriptions.

• Image Editing: Modify or partially edit existing images.

• Image Variants: Create different versions or stylistic variants of an image.

• Customizable Options:

  • Size: Supports multiple resolutions such as 1024×1024, 1024×1536, etc.

  • Quality: Choose from low, medium, or high rendering quality.

  • Format: Supports PNG, JPEG, WebP formats.

  • Compression: For JPEG and WebP, adjustable compression level from 0–100%.

  • Background: Supports both transparent and opaque backgrounds.

• API Access: Offers API interfaces for developers to integrate image generation capabilities into their own applications or services, supporting batch image generation.

Model Highlights

• Highly Accurate Instruction Following: Precisely understands and executes complex instructions to ensure accuracy in image generation.

• Extensive Artistic Styles: Supports a wide range of artistic styles for various creative needs.

• Advanced Image Editing: Enables precise image adjustments based on text prompts.

• Rich Real-World Knowledge: Generates images that reflect real-world contexts, increasing credibility and usability.

• Consistent Text Generation: Maintains textual coherence within images, ideal for use in educational materials, storybooks, and more.

Pricing for GPT-image-1

• Text Input Tokens: $5 per 1 million tokens

• Image Input Tokens: $10 per 1 million tokens

• Image Output Tokens: $40 per 1 million tokens

Project Link

• Official Website: https://openai.com/index/image-generation-api/

How to Use GPT-image-1

Step 1: Account Setup

Visit the OpenAI official website and register for an account. After registering, log in to obtain your API key.

Step 2: Install the OpenAI Python Library

pip install openai

Step 3: Configure API Key

import os
import openai

# Set API key
openai.api_key = os.getenv("OPENAI_API_KEY")

Step 4: Call the Image Generation API

Generate Image from Text

import openai
import base64

# Initialize OpenAI client
client = openai.OpenAI()

# Call the image generation API
result = client.images.generate(
    model="gpt-image-1",
    prompt="A futuristic cityscape at sunset with flying cars and neon lights",
    size="1024x1024",
    quality="high",
    background="transparent"
)

# Get the image data
image_base64 = result.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

# Save image to local file
with open("futuristic_cityscape.png", "wb") as f:
f.write(image_bytes)

Edit an Existing Image

import openai

# Initialize OpenAI client
client = openai.OpenAI()

# Call the image editing API
result = client.images.edit(
    model="gpt-image-1",
    image=open("input_image.png", "rb"),
    mask=open("mask.png", "rb"),
    prompt="Replace the sky with a starry night",
    size="1024x1024",
    quality="high"
)

# Get the edited image
image_base64 = result.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

# Save the edited image
with open("edited_image.png", "wb") as f:
f.write(image_bytes)

Generate New Image from Reference Images

import openai

# Initialize OpenAI client
client = openai.OpenAI()

# Call the image generation with references
result = client.images.edit(
    model="gpt-image-1",
    image=[
        open("body-lotion.png", "rb"),
        open("bath-bomb.png", "rb"),
        open("incense-kit.png", "rb"),
        open("soap.png", "rb"),
    ],
    prompt="Generate a photorealistic image of a gift basket on a white background labeled 'Relax & Unwind' with a ribbon and handwriting-like font, containing all the items in the reference pictures",
    size="1024x1024",
    quality="high"
)

# Get the result
image_base64 = result.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

# Save to file
with open("gift_basket.png", "wb") as f:
f.write(image_bytes)

Use Cases of GPT-image-1

• Adobe: Integrated into Firefly and Express for diverse image styles.

• Figma: Enables quick image generation and editing from simple prompts.

• HeyGen: Enhances avatar creation and editing capabilities.

• Wix: Helps users turn ideas into visuals effortlessly.

• Photoroom: Assists online sellers in creating studio-quality visuals from product photos.

Application Scenarios

• Creative Design: Quickly convert sketches into high-quality graphic elements with support for high-fidelity visual editing.

• E-commerce & Marketing: Generate product images, marketing posters, and social media visuals to enhance visual appeal.

• Brand Design: Create editable logos, brand visual assets, and professional layouts.

• Video Creation: Enhance video editing with high-quality avatars and animation effects.

• Education & Content Creation: Generate illustrations and creative content to assist in teaching and storytelling.