OpenAI adds Sketch tools to ChatGPT Images 2.5
OpenAI has rolled out ChatGPT Images 2.5, adding sketch-based creation, image comments, templates and more reliable multi-turn editing while cutting generation latency by up to half compared with Images 2.0. The upgrade, announced on September 8, is being made available across ChatGPT, ChatGPT Work and Codex on desktop, mobile and web. OpenAI said the model produces sharper details, more natural…
OpenAI has introduced ChatGPT Images 2.5, bringing sketch-based creation, image comments, templates and more reliable multi-turn editing. The upgrade, announced on September 8, cuts generation latency by up to 50% compared to Images 2.0. Users can now draw rough visual references using Sketch, add comments to indicate edits, and benefit from templates for common formats.
The model produces sharper details, more natural lighting and richer textures while maintaining subjects from reference photos consistently. It also handles complex instructions, infographic layouts and transparent backgrounds more accurately. OpenAI has launched two API models: GPT-Image-2.5 Flare for faster performance and GPT-Image-2.5 Sunburst for greater precision with longer generation times. Image generation is now more interactive, with direct visual guidance and focused correction.
Written by urgent.news from Arabian Post's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.