A practical product-image brief for GPT Image 2.5

A product-image prompt is easier to evaluate when it reads like a small photography brief. GPT Image 2.5 Flare and Sunburst are available on RouterBase for creating images and editing existing ones. Here is a simple way to prepare a first experiment.

Describe the placement first

Suppose you need a square concept image for a handmade mug. Decide where the mug sits, what the background looks like, and which side needs empty space. These decisions matter because a pleasing picture can still be unsuitable for the page where you plan to use it.

Try a brief like: “A matte blue ceramic mug on a warm beige surface. Soft light from the left. Eye-level view. Leave clear space above the mug for a heading. No additional objects.” This is an illustrative prompt, with no generated result attached.

Make the requirements observable

Write a short acceptance checklist before submitting. Is the handle visible? Does the composition leave the requested space? Is the surface free of distracting objects? If you request lettering, inspect the exact words at the size visitors will see. A model output needs review before it becomes a production asset.

Refine one decision

Keep the initial brief when changing the lighting or camera position. If you already have a suitable composition and want to change one element, consider the editing workflow. Describe the requested change and the elements that should remain consistent.

Use an output size suited to the final placement. Avoid judging a small website thumbnail only from a large preview. Save the original file, the prompt version, and your review notes so the next attempt has a clear purpose. Compare Flare and Sunburst using the same brief if your decision depends on which variant fits the task.

Choose the task and collect the result

RouterBase lists GPT Image 2.5 Flare and Sunburst with separate text-to-image and edit IDs. For a new image, submit to /v1/images/generations. The response supplies a generation ID while the task is pending. Save it, then poll /v1/images/generations/{id}. When the status is success, read data[0].url; when it is failed, inspect the error. Use an Idempotency-Key when retrying the same submission.

Read the RouterBase implementation guide.

评论

此博客中的热门博文

How to Access 200+ AI Models Through a Single API Endpoint

A support-ticket extraction exercise for DeepSeek V4.1 Flash

MiniMax H3 Prompting Starts Before the Prompt: Pick the Right Input Mode