ChatGPT Adds Images 2.5 Model, New Feature Turns Doodles Into AI Photos

<p>Months after updating ChatGPT's image generation with <a href="https://www.pcmag.com/news/openai-boosts-chatgpts-image-generator-with-web-access-multi-image-support" target="_self">Images 2.0</a>, OpenAI on Tuesday released an upgraded model and a new Sketch tool that turns your doodles into high-quality AI-generated imagery.</p><p>Images 2.5 is currently rolling out to all ChatGPT users on desktop, mobile, and web. Compared with the older model, it reduces image-generation latency by 50% and is better at producing natural light and rich textures, preserving subjects from reference photos, and following edit instructions across multiple iterations, OpenAI <a href="https://openai.com/index/introducing-chatgpt-images-2-5/" target="_blank" title="(Opens in a new tab)">says</a>.</p><p>The model also adds new Templates to help speed up your creative work. Instead of starting from scratch, you can now go to <strong>Images </strong>> <strong>Templates </strong>and choose from pre-set formats, including <strong>Poster </strong>and <strong>Merch</strong>, to generate desired outputs quickly.</p><div class="mb-0 rounded-md bg-gray-100 p-3 md:p-5" id="related-video">

<div class="flex items-center">

<div class="w-6 flex-none">

<img class="w-full" src="/images/pcmag-simplified.png" alt="PCMag logo">

</div>

<div class="pl-2 text-base leading-normal md:pl-3">