All models

gpt-image-2.5-sunburst

OpenAIImage
Get your API key
gpt-image-2.5-sunburst

High-Fidelity Image Model for Product Visuals and Precise Revisions

GPT Image 2.5 Sunburst is the image generation and editing model offered by this platform, positioned for high fidelity and precise control. It is suitable for product background adjustments, event visual revisions, and detail refinements based on existing assets. It can generate new images from text and edit images using reference images. Compared with Flare, which is positioned on the platform for rapid generation, Sunburst is better suited to creative tasks with a clear design direction that require repeatedly specifying what to preserve and what to modify.

Try this modelView pricing
OpenAIModel brand
ImageModel type
ImageTask capability

Specifications and API Features

Clarify capacity, input/output, and invocation methods before selecting a model.

Creation methods
Text-to-image generation; combined editing with reference images and text
Platform reference image input
A single URL or up to 16 URLs; local images can be uploaded using multipart
Platform image quantity
n is 1–10; the b64_json return method supports only 1 image
Platform canvas settings
auto or WIDTHxHEIGHT; width and height must be multiples of 16, with the longer side not exceeding 3840 pixels
Platform size limits
Total pixels 655,360–8,294,400, with an aspect ratio not exceeding 3:1
Platform result delivery
Image URL or Base64 image data; long-running tasks support asynchronous callbacks
Local editing method
The :official variant supports multipart Alpha PNG masks

The quantities, dimensions, and delivery methods above are within this platform's invocation scope and do not represent native model capacity claims; local mask editing uses the corresponding :official variant.

Core Capabilities

Learn what gpt-image-2.5-sunburst can bring to your work.

Make targeted changes based on the original image

Sunburst focuses on high fidelity and precise control, rather than simply generating images from scratch. When editing, you can specify both the background, lighting, or objects that need to change and the subject shape, colors, and composition that should be preserved. It is suitable when the design direction has already been determined and you want to reduce the work of remaking the entire image, while also making it easier to check each change against requirements.

Turn reference materials into creative constraints

By combining image and text inputs, you can propose new scene concepts around existing product photos, campaign key visuals, or character assets. Each reference image should have its purpose explained separately, such as subject appearance, background atmosphere, or color direction, to avoid making the model guess the relationship between materials. Outputs still need review; reference images do not mean every detail will be copied exactly.

Keep reversible versions throughout the revision process

With iterative revisions, you can use a selected result as the input for the next edit, handling the background, lighting, and local objects in sequence instead of redescribing the entire image every round. It is recommended to save each approved version and clearly specify what needs to be changed in the current round only. Organizing creation this way makes it easier to identify whether later changes have affected previously approved subject details.

Use Cases

Start with specific tasks to find where the model can be effective.

Change the setting of product images

Input a product photo and describe a new studio, holiday display, or lifestyle setting, while also listing preservation requirements such as the packaging outline, label content, and brand colors. Deliverables can be used for product presentation and marketing creative selection. If the product itself must remain unchanged pixel by pixel, composite the generated background with the original product asset rather than relying solely on the generated result.

Targeted revisions for campaign visuals

Use an existing campaign key visual as a reference, provide instructions to replace props, adjust the environment, or change the compositional focus, and specify the brand elements that must not change. This is suitable for exploring different options within an established visual direction, with outputs for designers to select and lay out. When titles, dates, and brand identifiers are involved, the final text content and placement should still be checked manually item by item.

Fine-tune a selected draft

Submit a selected generated draft to the editing entry point and focus on modifying background distractions, object colors, or lighting relationships. When mask control is needed, you can choose the :official variant to upload the original image and an Alpha PNG mask. The deliverable is an image version that can continue to be revised; during review, focus on comparing the modified areas, edge blending, and content that should be preserved.

How to choose this model

Choose based on task complexity, input materials, and expected results.

Choosing between Sunburst and Flare

If the task first requires quickly generating multiple concept directions, the speed-focused GPT Image 2.5 Flare is better suited as a candidate; if you already have materials and a clear list of edits, and want to refine product appearance or event details, prioritize Sunburst. You can also select a Flare draft first, then hand the image to Sunburst for editing. The choice between the two should be based on actual image results, without assuming a fixed degree of quality improvement.

Choosing between the standard ID and :official

gpt-image-2.5-sunburst and gpt-image-2.5-sunburst:official share a positioning focused on high fidelity and fine control; they do not represent two generations of models. Use the standard ID for regular text generation or revisions based on reference images; choose the :official variant when you need to upload masks according to the defined workflow. Explicitly provide the full ID in calls, and save image inputs, response methods, and specific parameters together to make it easier to reproduce and compare revision results.

Get started

From a small-scale task to production integration.

01

Prepare the task and materials

Define the goal, required inputs, and output requirements, using real business examples as a starting point.

02

Try it in the API testing area

Open the trial page, confirm the parameters supported by this entry point, then submit a small-scale task to review the results.

03

Integrate according to the API documentation

Keep the full model ID, use the request format specified in the documentation, and confirm billing rules on the Pricing page.

Usage limitations

Before formal use, understand output quality and capability boundaries.

  • High fidelity does not mean that the original image pixels remain completely unchanged. When modifying backgrounds or objects, subject textures, labels, people’s appearance, and surrounding lighting and shadows may still change; successive revisions may also affect details that were previously approved. If product photography must remain exactly as-is, use compositing and save approved versions after each round.
  • Text and layout still require review. Accurate wording, character clarity, title placement, and complex information hierarchy in posters cannot be guaranteed by prompts alone. It is suitable to generate visual concepts first, then check brand text, dates, and layout; finished products requiring strict typesetting can be completed in design tools.
  • Mask editing has separate input requirements: use the :official variant and place the original image and mask in the same multipart request. The mask must include an Alpha channel and be the same size as the first original image; URL-based original images and local masks cannot be mixed. Natural blending may still occur at edit edges.

Frequently Asked Questions

Answers to common questions about using gpt-image-2.5-sunburst.

Can Sunburst generate images directly from text?

Yes. Submit model=gpt-image-2.5-sunburst and prompt to /openai/images/generations to start text-to-image generation. Describe the subject, environment, lighting, and composition, and specify whether text is needed; if an existing image needs modification, use the editing endpoint.

How can I make reference image edits closer to the original design?

Submit the image and editing instructions to /openai/images/edits, and explicitly provide the Sunburst ID. The prompt should separately describe the intended changes and content to preserve; for multiple reference images, also specify the purpose of each. Focus on a clear goal in each round, and compare with the original image to check subject and brand details.

How should Sunburst masks be prepared?

The mask workflow uses gpt-image-2.5-sunburst:official, with both the original image and mask uploaded via multipart. The mask must be a PNG with an Alpha channel, the same dimensions as the first original image, and no larger than 4MB; transparent areas can be modified, while images with only black-and-white colors and no transparency channel cannot be used as a substitute.

Can I generate multiple images at once and return Base64?

The platform allows n to be set from 1–10, which is suitable for obtaining multiple candidate images; however, response_format=b64_json supports only 1 image. When multiple results are needed, use the URL return method; when Base64 image data must be processed directly, make a single-image request. Do not mix the two settings.

Will multi-round editing automatically remember previous images?

You should use the selected image as the input for the next edit, and state the changes and preservation requirements for the current round in the new instructions rather than relying only on prior requests. For long tasks, you can add callback_url, obtain task_id first, and receive the result upon completion; save the images and instructions from each round for easier comparison and rollback.

Model information · Updated: 2026-10-01. See the API and pricing sections for request parameters and billing rules.

Put gpt-image-2.5-sunburst to work on your next task

Start with a clear goal and judge whether it suits your work based on real results.

Start TryingView Pricing

More from OpenAI

dall-e-2dall-e-3gpt-image-1gpt-image-1.5gpt-image-2gpt-image-2.5-flare