OpenAI introduced ChatGPT Images 2.5, its latest image-generation model. It aims to improve visual quality, editing precision, and the overall creative process. The update brings sharper details, richer textures and more natural lighting, making image generation faster.
OpenAI says Images 2.5 can reduce image-generation latency by up to 50% compared with Images 2.0. The company also upgraded the model to handle reference photos and follow instructions across multiple editing rounds.
In a blog post, OpenAI explained, “People now create more than 3 billion images every week across ChatGPT Images and its GPT-Image models in the API. Now, with the new image-generation models, the AI firm aims to make images look more natural.”
The tech giant further added, “Images 2.5 is also designed to maintain consistency through multiple rounds of editing. Earlier changes are more likely to remain intact when users continue refining an image in the same conversation.”
The model also produces more natural lighting and richer textures. OpenAI says it has improved its understanding of complex visual instructions, layouts and styles, helping users create images that better match detailed creative briefs.
ChatGPT Images 2.5 is rolling out to ChatGPT, ChatGPT Work and Codex users across desktop, mobile and web. OpenAI says the update is available across all tiers.
For developers, OpenAI introduced GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst through its API. Flare targets faster, high-quality image generation, while Sunburst is designed for detailed creative workflows where greater editing precision is important.
Also Read: Sam Altman Says Sorry After GPT-6 Astra Rollout Leaves Paid Users Waiting