- OpenAI has launched a faster and smarter image model called GPT Image 1.5 inside ChatGPT.
- The new tool allows users to edit photos in detail and accurately and create their own visual effects based on tips.
- The new Images tab adds settings and filters without the need for written prompts.
OpenAI has updated and expanded its AI image creation capabilities. ChatGPT. The improvement came shortly after the release of the ChatGPT-5.2 model for everything else offered by AI. chatbot. The new GPT Image 1.5 is up to four times faster than its predecessor and designed for better editing and more reliable execution of instructions.
In its announcement, OpenAI presented the new ChatGPT images as a serious creative tool that produces professional-grade results. Despite all the caveats about the limitations of AI image generators, it's a bit like a slightly flawed but powerful visual production studio run by someone who understands regular language so you don't have to fiddle with sliders and layers.
The new model also contains some changes to ChatGPT. ChatGPT now has a dedicated Images tab that serves as a hub for creating images with pre-built filters and options curated based on current trends. There are also templates that let you create or edit images without even entering a hint. You can click on “retro magazine layout” or “futuristic food style” and see what it looks like without having to figure out the best wording for the prompt, which is part of OpenAI's efforts to make the tool as accessible as possible.
The new model also has many other small improvements. It can create denser text without turning into nonsense, show a crowd of small faces without creating too many oddballs, and can track elements across multiple edits so you can change one aspect of an image without the AI deciding to tinker with other parts. Past models could easily become confusing due to chain editing or duplicate instructions.
The update also allows you to better combine and transform images. You can ask it to mix styles, move part of one image into another, or remove all but one component and move it to a new setting. You also won't have to worry too much about the space between people or objects getting confusing.
AI Image Enhancement
However, it's not ideal. Some results fall short of the target. Sometimes a model will misinterpret a phrase or convey something too literally. But the difference now is that these moments seem to be the exception, not the norm. At least that's what OpenAI claims.
There's more to it than just what you can do with the OpenAI model. Adobe It recently became clear that this is Photoshop embedding and Acrobat in ChatGPT. This means we're moving towards a future where multiple editing platforms live side by side. You can have ChatGPT create a poster and then jump into Photoshop to enhance it without ever leaving the same window.
ChatGPT has no shortage of AI image competition from companies like Google Gemini and Midjourney, but ChatGPT's random access to images means you can turn to it to create things like an improved headshot on LinkedIn before specifically opening Midjourney.
The most positive interpretation of the updated ChatGPT images is that a new level of high-quality visual creativity is no longer limited by technical skills or expensive software. But it comes with all the caveats and uncertainty about how much of what ChatGPT creates is simply remixed content pulled without the consent of human artists, not to mention how much its use disempowers professionals in the field. No matter how exciting and impressive the results are, it still means that users will have to decide what exactly it means to “do” something in the first place.
Follow TechRadar on Google News. And add us as your preferred source to get our expert news, reviews and opinions in your feeds. Be sure to click the “Subscribe” button!
And of course you can also Follow TechRadar on TikTok for news, reviews, unboxing videos and get regular updates from us on whatsapp too much.
The best business laptops for any budget.
