Image to Image

GPT Image 2

OpenAI's latest image editing model with multi-image support.

Schema
Add images (0/16)

Upload up to 16 images

Example
Example output

Sample output shown above. The prompt and settings are pre-filled on the left.

Your request will cost $0.06 per run. For $10 you can run this model approximately 166 times.

One more thing:

README

OpenAI / GPT Image 2 β€” Image to Image (gpt-image-2-i2i)

GPT Image 2 transforms existing images with near-perfect text rendering and support for multi-image inputs.

Highlights

  • β€’Multi-image editing – Combine and transform multiple source images.
  • β€’Near-perfect text – Over 99% text rendering accuracy.
  • β€’Flexible editing – Powerful prompt-based transformations.

Parameters

  • β€’image* – Source images to transform (up to 16 images)
  • β€’prompt* – Description of the transformation (up to 20,000 characters)

Pricing

$0.06 per generation

How to Use

  1. 1.Upload one or more source images.
  2. 2.Write a prompt describing the transformation.
  3. 3.Generate and download.

More Models to Try

β€’Photo editing: Transform and enhance photos with text overlays.
β€’Style transfer: Apply artistic styles with text elements.
β€’Composite creation: Combine multiple images into one.

Frequently Asked Questions

What is the GPT Image 2 API?
OpenAI's latest image editing model with multi-image support.
How much does GPT Image 2 cost via API?
GPT Image 2 costs $0.0600 per generation through Renderful's API. No subscription required β€” pay only for what you use.
How do I use GPT Image 2 via API?
Sign up for a free Renderful API key, then send a POST request to the /v1/predictions endpoint with model "gpt-image-2-i2i". See the documentation at renderful.ai/docs for code examples in Python, JavaScript, and cURL.
What type of content does GPT Image 2 generate?
GPT Image 2 is a image to image model by OpenAI. Key features include: Multi-image input, Near-perfect text, 20K char prompts.
Is the GPT Image 2 API fast?
GPT Image 2 has medium generation speed. Results are delivered via polling or webhook callback for seamless integration.