ChatGPT Sketch turns your bad drawings into detailed AI images — SkimNews
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- OpenAI announced ChatGPT Images 2.5 on Tuesday, claiming "more natural lighting and richer textures," better instruction-following across multiple turns, and generation latency reduced "up to 50% compared with Images 2.0."
- The new Sketch feature lets users draw a doodle directly inside ChatGPT — activated by typing @Sketch in the chat — and renders it into a detailed image based on accompanying text instructions.
- ChatGPT now lets users leave comments directly on parts of an image to request targeted edits, such as changing a generated cat's eyes from blue to green.
- Images 2.5 rolled out immediately to ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web.
Why it matters: Sketch plus region-specific commenting shifts image generation from text-prompt guesswork to a visual collaboration loop, lowering the bar for non-artists. The 50% latency cut tightens iteration speed for ChatGPT Work and Codex users building images into professional workflows.
Ask SkimNews
