OpenAI on December 17 announced the release of a new version of ChatGPT Images, powered by its flagship image generation model, GPT Image 1.5, marking a major upgrade to how users create and edit images using AI.
The update is rolling out globally to all ChatGPT users and API customers, with OpenAI promising faster image generation, more precise edits, and better preservation of original image details.
What is new in ChatGPT Images?
The latest ChatGPT Images model allows users to generate images from scratch or edit existing photos with far greater accuracy. OpenAI says the model can produce images up to four times faster while keeping key elements—such as lighting, composition, and people’s appearance—consistent across edits.
A new Images feature inside ChatGPT also introduces a dedicated creative space, making image exploration easier through preset styles, filters, and prompts.
More precise image editing
One of the biggest improvements is in instruction-following. When users edit an uploaded image, the model now changes only what is requested, while preserving everything else. This enables:
-More realistic photo edits
-Believable clothing and hairstyle try-ons
-Cleaner stylistic filters and conceptual transformations
The model supports advanced editing functions such as adding, removing, blending, combining, and transposing elements without degrading the original image quality.
Better creativity and text rendering
OpenAI says the model excels at creative transformations, including adding text, adjusting layouts, and reimagining visuals while retaining the essence of the original image. Text rendering has also improved, allowing the AI to handle denser and smaller text more accurately.
Additional quality upgrades include better handling of multiple small faces and more natural-looking outputs, making images more usable for real-world applications.
GPT Image 1.5 in the API: Lower cost, stronger output
The same improvements are available through the GPT Image 1.5 API, which OpenAI says is significantly better at image preservation and brand consistency than its predecessor. This makes it particularly useful for:
-Marketing and brand design
-Logo and graphic creation
-Ecommerce product catalogs generated from a single source image
OpenAI has also reduced image input and output costs by 20% compared with GPT Image 1, allowing developers and businesses to generate more images within the same budget.
According to OpenAI, enterprises and startups across creative tools, ecommerce, marketing software, and other industries are already using GPT Image 1.5. Developers can try the model via the OpenAI Playground or explore best practices through the official prompt guide.
Availability and what’s next
The new ChatGPT Images model is available globally starting today across ChatGPT and the API, with no manual model selection required. The earlier version of ChatGPT Images will remain accessible as a custom GPT.
OpenAI calls this release a meaningful step forward in AI image generation, with future updates expected to bring finer-grained edits, richer visuals, and broader language support.
About the Author
