Introducing ChatGPT Images 2.5
If you use ChatGPT to create marketing images, social graphics or product mockups, this update makes edits faster and more predictable — sketch a rough reference or apply a saved template instead of rewriting a prompt from scratch. Developers get two new API image models if they need to build image generation into their own tools.
What changed
Source summary
OpenAI released ChatGPT Images 2.5, an upgraded image generation and editing model with faster generation (about 50% lower latency), sharper detail, and more reliable multi-turn editing. New tools include Sketch (draw a reference), Templates, and comment-based editing, rolling out to ChatGPT and ChatGPT Work users, alongside two new API models (GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst).
Why it matters to your work
Practical interpretation
If you use ChatGPT to create marketing images, social graphics or product mockups, this update makes edits faster and more predictable — sketch a rough reference or apply a saved template instead of rewriting a prompt from scratch. Developers get two new API image models if they need to build image generation into their own tools.
When this could help
Worth trying if you use ChatGPT for image creation or editing, especially if latency or edit precision has been a pain point.
ChatGPT Images 2.5 delivers sharper details, more precise editing, and up to 50% lower latency than 2.0. New features include Sketch (draw rough shapes and ChatGPT renders them), Templates (reusable image layouts), Comments on images (annotate for targeted edits), and prompt sharing. API users get two model variants: Flare (default, fastest) and Sunburst (premium, tighter control).
How to get started
Ask ChatGPT to create or edit an image as usual — it will use the new 2.5 model. For Sketch, type @Sketch and draw a rough shape for ChatGPT to render. Use Templates for reusable layouts, and Comments to annotate images for targeted edits.
Provider guidance ↗
Try this · The SCALA method
Give AI a clearer brief
- Situation
- You want to create or refine a visual using ChatGPT's image capabilities.
- Consultant
- Act as a visual designer helping me produce a polished image.
- Action
- Create [describe the image]. Then I will comment on specific areas for refinement. [Fill in your actual image request.]
- Language
- Visual output with iteration via comments.
- Ask
- After the first version, annotate and comment on the areas that need refinement rather than re-describing the whole image.
SCALA suggested prompt · Adapt the context and check the result.
Learn the SCALA method →Build it into your routine
SCALA suggested workflow
Iterative image editing
Use Comments to annotate specific areas of a generated image for targeted refinement instead of re-prompting from scratch each time.
What to check
Sources & provider guides
Official documentation checked 12 Oct 2026. SCALA prompts and workflows are suggestions, not claims of hands-on testing.
Source & availability
This is a summary of a published provider announcement, with practical context from SCALA’s feed.
Plan, region, workspace and rollout conditions may affect access in Australia. Check the original source for current availability.
openai.com