OpenAI has released ChatGPT Images 2.5, a new state-of-the-art image model that delivers sharper details, more precise editing capabilities, and up to 50% faster generation compared to the previous version.
- The model produces more natural lighting, richer textures, and better preservation of subjects in reference photos.
- New features include Sketch for drawing visual guides, Templates for popular formats like flyers, and the ability to share prompts with images.
- Two API models are available: GPT-Image-2.5 Flare as the default high-speed option and GPT-Image-2.5 Sunburst for premium, detailed creative work.
- The update improves reliability across multiple editing turns, allowing users to make focused changes without degrading image quality over time.
This release expands what users can create with ChatGPT Images 2.5, offering better control over the creative process and faster workflows for both individual creators and developers building image generation applications.