ChatGPT Images 2.0 is here with improved photorealism, better Hindi text rendering and more
Follow UsOpenAI has introduced ChatGPT Images 2.0.
The company also says that the created images will now look 'less AI-generated and more intentionally designed.'
One of the biggest improvements in Images 2.0 is greater precision and control.
OpenAI has introduced ChatGPT Images 2.0, a new image generation model designed to create more accurate and useful visuals. The company says the upgrade focuses on producing images that are not only visually appealing but also practical for real-world tasks like presentations, marketing material, explainers and design projects.
SurveyAccording to OpenAI, the new model better understands prompts and turns them into images. It can better follow detailed instructions, place objects correctly and render small elements. The company also says that the created images will now look ‘less AI-generated and more intentionally designed.’
Also read: ‘Legend’: Sam Altman and other leaders react as Tim Cook steps down as Apple CEO
Here is a manga made by ChatGPT Images 2.0 of @gabeeegoooh and me looking for more GPUs: pic.twitter.com/ek95JfUN5V
— Sam Altman (@sama) April 21, 2026
OpenAI’s ChatGPT Image 2.0 AI model: Key capabilities
One of the biggest improvements in Images 2.0 is greater precision and control. The model can handle more complex prompts and preserve specific details. This includes generating small text, iconography, UI elements, dense compositions and subtle stylistic constraints.
With ChatGPT Images 2.0, OpenAI has also improved multilingual support. Earlier image models worked best with English or Latin-based languages, but Images 2.0 now performs much better with languages such as Hindi, Bengali, Japanese, Korean and Chinese.
Also, according to OpenAI, ChatGPT Images 2.0 is better to ‘capture the defining characteristics of photos—including the tiny flaws that add realism—as well as cinematic stills, pixel art, manga, and other distinctive visual languages, with greater consistency in texture, lighting, composition, and fine detail.’
Also read: Tim Cook steps down: Full text of his memo to Apple employees
ChatGPT Images 2.0 also introduces thinking capabilities. When you select a thinking model in ChatGPT, the system takes more time to analyse a request, search the web for real-time information, and even generate multiple images from a single prompt.
‘Images 2.0 acts more like a visual thought partner, helping carry a project from rough concept to finished asset with significantly less work on your part,’ OpenAI explained.
Availability
OpenAI’s ChatGPT Images 2.0 is available to all ChatGPT and Codex users. Note that the thinking capabilities feature is only available to ChatGPT Plus, Pro and Business users.
