OpenAI launches ChatGPT Images 2.5 with faster generation and sharper edits

OpenAI has released ChatGPT Images 2.5, a new image-generation model aimed at making creative work faster, more consistent, and easier to refine. In its OpenAI News announcement, the company says people now create more than 3 billion images each week across ChatGPT Images and GPT-Image models in its API.

The update brings sharper detail, richer textures, more natural lighting, and stronger preservation of subjects from reference photos. OpenAI also says the model follows editing instructions more reliably over multiple turns. Generation latency is reduced by up to 50% compared with Images 2.0, which could make iterative workflows less frustrating for designers, marketers, and developers building image features into their products.

New controls for creators

ChatGPT users get several workflow additions. Sketch lets people draw a rough visual reference directly in ChatGPT, while templates provide starting points for formats such as flyers and product photos. Users can also add comments to specific images for more focused revisions and share the prompts behind their creations so others can adapt them with their own photos and details.

Images 2.5 is available across desktop, mobile, and web for ChatGPT, ChatGPT Work, and Codex users.

For developers, OpenAI is introducing two API models: GPT-Image-2.5 Flare, which carries over the new quality, editing, and speed improvements, and GPT-Image-2.5 Sunburst, designed for more precise creative work at the cost of longer generation times. The release gives teams more options for balancing speed, fidelity, and control in reference-driven image pipelines.

Source: OpenAI News