OpenAI Releases GPT Image 1.5 for Faster and More Accurate Image Generation

Dec 17, 2025
OpenAI has released GPT Image 1.5, a new version of its ChatGPT Images model offering faster generation, improved instruction following, and more precise editing. The update is rolling out to all ChatGPT users and through the API.

OpenAI announced in a press release the launch of GPT Image 1.5, an upgraded image generation model now available in ChatGPT and via API. The update delivers up to four times faster image creation, stronger adherence to user instructions, and improved preservation of details such as lighting, composition, and likeness across edits.

The new model enhances ChatGPT Images with advanced editing capabilities, allowing users to make precise changes—like altering facial expressions or lighting—without losing consistency. It also improves text rendering and supports more expressive transformations, helping users maintain key visual elements while reimagining scenes.

A new dedicated Images interface in ChatGPT’s sidebar lets users explore preset filters, trending prompts, and upload likenesses for reuse in future creations. This design aims to make image generation more intuitive and interactive, supporting both minor edits and complete redesigns.

GPT Image 1.5 is also available through the API, offering 20% lower costs compared to its predecessor and better performance for tasks like logo creation and product catalog generation. The rollout to all ChatGPT users and API clients began globally on December 16, 2025.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.