# OpenAI Ships Images 2.5 as Provenance Rules Tighten on Generated Media

The model generates up to 50 percent faster and adds sketch input, arriving in the same season Anthropic began watermarking Claude's text output.

- Published: 2026-09-09T06:20:57.202Z
- Canonical: https://polylog.news/ai/2026-09-09/openai-ships-images-2-5-as-provenance-rules-tighten-on-gener
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [OpenAI](https://openai.com/index/introducing-chatgpt-images-2-5), [Polylog editors](https://polylog.news), [Anthropic News](https://www.anthropic.com/news/claude-text-watermark)

OpenAI released ChatGPT Images 2.5 on September 8, five months after Images 2.0. The company reports generation up to 50 percent faster, more reliable multi-turn editing, better preservation of subjects from reference photographs, and a Ske…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-09/openai-ships-images-2-5-as-provenance-rules-tighten-on-gener (subscription information: https://polylog.news/pricing).