OpenAI said on Tuesday that it is rolling out a new version of ChatGPT Images, introducing a model called GPT Image 1.5 that offers faster image generation, stronger instruction-following, and more precise editing controls.
New Image Model Available to Users and Developers
GPT Image 1.5 is available to all ChatGPT users and through OpenAI’s API. The company said the model can generate images up to four times faster than its previous version and improves accuracy when users request specific changes.
The release follows OpenAI’s earlier image model, GPT Image 1, which launched in April.
Competitive Context With Google
The update arrives amid increased competition with Google. In a leaked internal memo last month, OpenAI chief executive Sam Altman described a “code red” response to Google’s recent gains in the AI market.
Google’s Gemini 3 model and its image generator, Nano Banana Pro, have ranked highly on the LMArena leaderboard across multiple benchmarks. OpenAI responded last week with the launch of GPT-5.2, which it described as its most advanced model so far for developers and professional use.
OpenAI had reportedly planned to release a new image model in early January but moved forward with the rollout this week.
More Granular Image Editing
OpenAI said GPT Image 1.5 improves post-production workflows by allowing more controlled edits that preserve visual consistency. The model supports targeted changes to elements such as facial likeness, lighting, composition, and color tone.
The company said many generative image tools struggle with iterative edits, often reinterpreting an entire image when asked to make a small adjustment. GPT Image 1.5 is designed to handle those requests with less disruption to the original image.
New Interface for Image Creation
ChatGPT Images will now be accessible through a dedicated section in the ChatGPT sidebar. Fidji Simo, OpenAI’s chief executive of applications, said the new entry point is designed to function more like a creative workspace.
In a blog post, Simo said updated viewing and editing screens are intended to make it easier for users to create images that align with their ideas or explore trending prompts and preset filters.
Broader Visual Updates in ChatGPT
Alongside the image model, OpenAI is adding more visual elements to the ChatGPT experience. Simo said search queries will increasingly surface visual results with clear source references, which may assist with tasks such as unit conversions or checking sports scores.
She said the goal is to allow users to see and shape what they are creating directly within ChatGPT, while also presenting visuals when they convey information more effectively than text alone.
Featured image credits: Pexels
For more stories like it, click the +Follow button at the top of this page to follow us.