News + Trends
In future, you will be able to set preferred sources on Google
by Samuel Buchmann
GPT image 1.5: more speed and control for AI images
17.12.2025
Translation: machine translated
Pictures: Kim Muntinga
With GPT-Image 1.5, OpenAI is expanding the image functions of ChatGPT. A new image view bundles the creation and editing of visual content and is designed to work more precisely and faster than previous solutions.
OpenAI has introduced GPT-Image 1.5, a new model for image generation which is directly integrated into ChatGPT. The new Images view in ChatGPT allows users to create images, edit uploaded photos and further develop visual content in a targeted manner. All within a centralised interface.
Faster and more precise: the new model
According to OpenAI, the new model is significantly faster than its predecessor and implements instructions more precisely. The tech company speaks of up to four times faster speed and improved instruction processing, which facilitates targeted changes to images and reduces unintentional style breaks.
Custom images view for visual work
The new images view in ChatGPT puts image generation and editing centre stage. Users can realise image ideas directly, compare variants and edit previous results again. The chat remains part of the workflow so that concepts and texts can continue to be developed in dialogue.
In addition to classic text-to-image generation, OpenAI is now focussing more on editing existing images. Uploaded photos can be specifically modified, individual areas can be masked, replaced or added to. This is controlled exclusively via text commands. According to OpenAI, the function is not intended as a replacement for professional image editing software, but rather as a solution for quick drafts, illustrations and editorial adjustments.
Classification in the AI image generator market
In comparison to specialised image generators such as Midjourney or Stable Diffusion, OpenAI takes a different approach: image generation is integrated into a universal AI platform and focuses on accessibility and context integration. While Midjourney is often the leader in aesthetically sophisticated single images and Stable Diffusion offers technical flexibility, ChatGPT Images emphasises workflow efficiency and ease of use. The decisive difference lies less in the pure image quality than in the integration of text, image and editing in one system.
Google is pursuing a different focus with Gemini Imagen 4 and Nano Banana Pro. The new tools primarily emphasise high image quality, improved text integration and direct integration into Google Workspace applications. Nano Banana Pro also addresses more structured content such as infographics or data-based visualisations.
While Google clearly embeds its image generators in productive work environments, OpenAI positions ChatGPT Images as a low-threshold, versatile tool. The difference lies less in the pure image quality than in the respective orientation: here integration into existing office workflows, there a universal AI workspace.
Header image: Gargantiopa / Shutterstock
My interests are varied, I just like to enjoy life. Always on the lookout for news about darts, gaming, films and series.
News + Trends
From the latest iPhone to the return of 80s fashion. The editorial team will help you make sense of it all.
Show allThese articles might also interest you
2 comments
later