OpenAI released ChatGPT Images 2.5 on September 8, 2026, saying it improves image generation speed and editing precision for creative workflows. It is the company's first major update to its image model since the release of Images 2.0.
OpenAI reported a 50% reduction in image generation latency, measured against the performance of Images 2.0. That compares with the earlier model's slower response times.
ChatGPT Images 2.5 is built on the company's advanced image generation architecture and targets creative professionals, marketers, and developers. Availability begins today, initially for ChatGPT, ChatGPT Work, and Codex users across all platforms.
"What impressed us most about GPT‑Image‑2.5 Flare is how well it understands what not to change," said Axultan Alimkulov, Head of Product at Higgsfield AI. "You can make a meaningful edit without losing the character, composition or visual identity of the original image."
The announcement follows the continued expansion of OpenAI's image generation capabilities. OpenAI said the update supports more complex visual instructions and maintains image fidelity across multiple edits.
OpenAI did not say how the new model will perform in comparison to other image models, and it raised the question of how the improvements will affect existing workflows. The company said it will continue to refine the model based on user feedback.
Source: openai
