OpenAI has launched ChatGPT Images 2.0, a "thinking" image generator that is described as an advanced model capable of tackling complex visual tasks and producing precise, ready-to-use visuals.
Introducing ChatGPT Images 2.0
— OpenAI (@OpenAI) April 21, 2026
A state-of-the-art image model that can take on complex visual tasks and produce precise, immediately usable visuals, with sharper editing, richer layouts, and thinking-level intelligence.
Video made with ChatGPT Images pic.twitter.com/3aWfXakrcR
The company highlighted a "qualitative leap" in following instructions, accurately positioning and proportioning objects, and visualizing dense text.
The model effectively handles multiple languages and autonomously fills in gaps in requests based on visual and general context, resulting in users receiving the desired outcome with fewer clarifications.
Accuracy and Control
ChatGPT Images 2.0 excels at conceptualizing complex ideas and accurately rendering them visually.
The model adheres to instructions, maintains specified details, and displays fine elements with resolutions up to 2K.
Greater Precision and Control
— OpenAI (@OpenAI) April 21, 2026
ChatGPT Images 2.0 can conceptualize more sophisticated images, and then actually bring that vision to life effectively.
It’s able to follow instructions, preserve requested details, and render the fine-grained elements that often break image… pic.twitter.com/n29165pV9Q
Working with Styles
ChatGPT Images 2.0 more accurately conveys the distinctive features of photographs, cinematic frames, pixel art, manga, and other visual styles. The LLM ensures a high degree of consistency in textures, lighting, composition, and fine details.
This level of precision can be beneficial for creating game prototypes, developing storyboards, preparing marketing materials, and producing works in specific media formats or genres.
It Can Think
ChatGPT Images 2.0 is OpenAI's first image model capable of reasoning before generating images.
When paired with ChatGPT, the model can search for real-time information online, create multiple variations from a single prompt, verify results, and generate functional QR codes.
"This allows the model to take on much of the heavy lifting between the idea and the image, especially when accuracy, relevance of information, consistency, and visual integrity are paramount," OpenAI stated.
The model supports aspect ratios from 3:1 in width to 1:3 in height. It is available to ChatGPT and Codex users.
The Images with Thinking feature is included in the ChatGPT Plus, Pro, and Business plans.
As a reminder, in April, OpenAI opened access to the new AI model GPT-5.4-Cyber for a limited number of users.