OpenAI announced on Tuesday the release of ChatGPT Images 2.5, a major update to its image generation technology that offers sharper details, more natural lighting, and richer textures. The update significantly improves the model's ability to follow complex editing instructions across multiple turns and enhances its ability to preserve subjects when using reference photos.
Product LaunchesOpenAIChatGPT Images 2.5
OpenAI Unveils ChatGPT Images 2.5 with Sketch Feature and Faster Generation
A key new feature is "Sketch," which allows users to draw doodles directly within ChatGPT to serve as a visual guide for the final image. This feature is designed to provide more control over composition and layout, making the creative process more intuitive for users who may not be proficient in prompt engineering. Additionally, OpenAI introduced templates for common formats such as posters and product photos, as well as the ability to place comments directly on images for targeted editing.
In terms of performance, OpenAI states that image generation latency has been reduced by up to 50% compared to Images 2.0. The update is being rolled out to all ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web platforms.
For developers, OpenAI is introducing two new models via its API: GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst. Flare is designed as a high-speed, high-efficiency default model, while Sunburst is optimized for premium workflows requiring maximum precision and control over fine details. OpenAI continues to implement safety measures, including C2PA metadata and invisible watermarking via SynthID, to ensure transparency and provenance.