Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

Read original
OpenAI News·Sep 8, 2026, 11:30 AM

OpenAI Introduces ChatGPT Images 2.5

Original title:Introducing ChatGPT Images 2.5

Products83

OpenAI has rolled out ChatGPT Images 2.5, expanding multimodal generation by supporting user-supplied sketches and reference photos alongside text prompts. Instead of relying solely on iterative phrasing to capture an aesthetic, creators can now provide direct visual anchors to shape composition, styling, and individualized details. The update nudges ChatGPT’s visual pipeline toward more deterministic, design-oriented workflows.

Why it's worth reading

By integrating sketches and reference photos directly into the prompt workflow, ChatGPT Images 2.5 shifts generative visuals from speculative prompt tuning toward practical, deterministic creative control.

Tags

OpenAIChatGPTChatGPT ImagesImage GenerationMultimodalComputer Vision

Score breakdown

  • Novelty72
  • Impact84
  • Practicality88
  • Credibility92
  • Timeliness82