ChatGPT Sketch turns doodles into prompts for detailed AI images
OpenAI announced ChatGPT Images 2.5 with Sketch, a doodle-based prompting feature, plus direct comments for requesting image edits. OpenAI says the update is available across ChatGPT, ChatGPT Work, and Codex on desktop, mobile, and the web.
DNA Brief
Signal Summary
Users can type @Sketch in the ChatGPT input box to open a drawing window, then describe how the doodle should be turned into an image. OpenAI says Images 2.5 delivers more natural lighting and richer textures, follows editing instructions better across multiple turns, and cuts image-generation latency by up to 50% versus Images 2.0.
Why It Matters
Sketch adds a visual starting point to image prompting, allowing users to combine a rough composition with text instructions instead of relying on text alone. Direct comments on image areas and the claimed latency reduction could make iterative image editing faster.
Evidence
Start with the primary evidence, then review supporting sources and context.
Primary Evidence
1ChatGPT Sketch turns your bad drawings into detailed AI images
Jay Peters
“OpenAI announced ChatGPT Images 2.5 on Tuesday and is adding a new way to tell ChatGPT what you want it to make an image of: by drawing a doodle. With a new feature called Sketch, you can just draw something right inside ChatGPT and then tell ChatGPT how you want it to make an image [...]”
Recommended signals
Recommended by brand, topic, and recent confidence movement