OpenAI said on September 9 that it is making ChatGPT Images 2.5 available to ChatGPT, ChatGPT Work, and Codex users on desktop, mobile, and the web.

The update adds Sketch, templates, image comments, and prompt sharing.

OpenAI also introduced two new application programming interface models, GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst.

The company said ChatGPT Images 2.5 improves multi-turn editing consistency and cuts image generation latency by up to 50% compared with Images 2.0.

OpenAI said people create more than 3 billion images each week across ChatGPT Images and GPT-Image API models.

The company said the system retains safeguards including prompt and image checks, C2PA metadata, and invisible watermarking.

C2PA, or Coalition for Content Provenance and Authenticity, is part of a broader provenance standard that uses metadata to show a file’s source and integrity.

C2PA metadata and invisible watermarks can complement each other because metadata can be stripped. Using both can help platforms identify synthetic media.

🔗 Source: OpenAI

Recent OpenAI developments