Every good briefing I have sat in ended with a doodle on a napkin. Nobody remembers exactly what was said; everybody remembers the drawing.
OpenAI has put the napkin into the chat. The new feature is called Sketch: you roughly draw the room, the silhouette of a garment or just a funny doodle, and ChatGPT turns it into a finished image.
Fact
The facts: on 8 September 2026 OpenAI introduced ChatGPT Images 2.5, a new image model available to ChatGPT, ChatGPT Work and Codex users across all tiers on desktop, mobile and web. Per the company, generation latency is up to 50% lower than Images 2.0, the model preserves subjects from reference photos better and follows editing instructions more reliably across multiple turns. The new features in ChatGPT are Sketch (drawing in the chat as a visual guide, called with "@Sketch"), templates for popular formats such as posters and merch, comments placed directly on the image, and sharing the prompt along with the finished picture. The API gets GPT-Image-2.5 Flare, offered as the default choice for most applications, higher quality than GPT-Image-2 at 50% lower latency, and GPT-Image-2.5 Sunburst for premium work with tighter control and longer generation. According to OpenAI, more than 3 billion images are created every week across ChatGPT Images and the GPT-Image models in the API. Images continue to carry C2PA metadata and an invisible watermark.
Why the sketch matters more than the speed
You will feel the speed right away and forget it within a week. The sketch changes the way you talk to the machine.
Until now everything went through words. You describe a composition you see in your head, the model reads it its own way, you correct with more words. Anyone who has written a brief knows how much gets lost on the way. A line on paper says where the horizon is, where the person stands and where the light comes from, without arguing over what "left" means.
Words describe the picture. A sketch places it.
The second thing worth noting is a quiet one: a comment placed directly on the image. You point at the spot and say what you want there. That is how you work with every designer in the world; ChatGPT just didn't have it until now.
The quality and speed claims are OpenAI's. The real test will come from everyday client work, not from the launch demo.
If you make visuals for clients, try the sketch with something you have already drawn by hand. That is where you will see fastest whether the model listens to the line or only uses it as an excuse.
Official primary sources
OpenAI - Introducing ChatGPT Images 2.5, 08.09.2026The visual is generated code-art, no third-party images.