GPT Image 2.5 Flare is an image generation and editing model focused on generation speed, suitable for turning creative briefs into advertising visuals, interface concepts, and product scene images. It can also adjust colors, backgrounds, and composition using reference images. It is better suited to creative workflows that explore directions first and then select and refine; Sunburst in the same series focuses on high fidelity and fine control, making it suitable for tasks with higher requirements for detail preservation.
Submit requests to the public API at api.acedata.cloud using the documented parameters, then use the results in your application.
Input parameters and result formats vary by service. Use the public API for this model and follow its guide for generation, task retrieval and editing operations.
The quantities, dimensions, and formats above are invocation rules for this platform endpoint and do not represent the model's native specifications or guarantee the results of all parameter combinations.
Flare is suitable for organizing requirements for subjects, scenes, lighting, color palettes, and composition into comparable image concepts. When creating marketing assets, you can explore different backgrounds and visual styles around the same theme, first select the most suitable direction, then continue refining the chosen image instead of locking in a complex final version from the start.
When editing, you can submit product photos or existing designs and clearly specify the subjects, angles, and layouts to retain, as well as the colors, environments, and backgrounds you want to change. Multiple reference images can be used to express different visual requirements, but the role of each image should be explained to avoid treating conflicting compositions or styles as simultaneous goals.
Generation and editing each use dedicated image endpoints, and the output remains an image rather than an editable design project. Applications can receive image links or use Base64 image data; for longer-running tasks, asynchronous callbacks can separate task submission from asset ingestion, making subsequent review and delivery easier.
Enter the campaign theme, target audience, product features, and placement format to generate a set of poster or social media image alternatives. Use text to specify the subject position, background atmosphere, and copy whitespace separately, then select compositions suitable for placement. Before delivery, add accurate brand elements and verify that text in the image and the product appearance meet requirements.
Enter the page objective, module order, brand colors, and desired interface style to create visual concepts for landing pages or app screens. It is suitable for discussing layout atmosphere, illustrations, and information hierarchy, while the deliverable is a concept image; component dimensions, interaction states, typography specifications, and functional pages still need to be completed during design and development.
Use product photos or scene descriptions as input to explore seasonal backgrounds, lighting, and promotional settings, and also create video opening frames and storyboard sketches. Prompts should describe the camera angle, subject position, and details that must be retained; after obtaining static images, pass them to subsequent design or video production workflows for continued use.
When the task involves everyday supporting visuals, creative proposals, and multi-round direction exploration, Flare's speed-oriented approach better aligns with the work objective. If you need to preserve product structure as much as possible, make fine adjustments to local content, or require greater consistency with reference images, compare GPT Image 2.5 Sunburst. Use the same assets and instructions, and judge the trade-off by usable generated images rather than model names.
GPT Image 2 is a related previous-generation model; its example results should not be directly regarded as Flare's results. gpt-image-2.5-flare and gpt-image-2.5-flare:official should also be used as different calling IDs. They share Flare's basic positioning, but parameters and billing must be configured separately; do not assume that all request syntax is exactly the same just by adding a suffix.
Provide prompt when generating; provide both image and editing instructions when editing. Clearly specify the original text, subject preservation requirements, and target aspect ratio.
Use the image generation or image editing endpoint, and explicitly specify model=gpt-image-2.5-flare; use auto or WIDTHxHEIGHT for size, generate one image first, then evaluate. Set masks, quality, and file format according to this endpoint guide.
Read the URL or Base64 image according to the response format, save task_id asynchronously before querying the result; check text, reference details, and the alpha channel, and record usage according to the current Pricing rules.
Create three distinct visual directions for a portable coffee cup. Start by trying one: a bright orange background, the cup on the left, large text “Take a Break” on the right, and a lighthearted brand atmosphere.
Use a low-complexity brief to quickly compare visuals, then narrow down the directions; the settlement method for per-image calls and token-metered variants should be confirmed separately in Pricing.
Flare focuses on generation speed and is suitable for everyday image creation, creative alternatives, and quick edits; Sunburst focuses on high fidelity and fine-grained control. If the task emphasizes product details, reference image consistency, or complex editing, compare Sunburst first; if the main goal is to explore visual directions, start with Flare.
Use /openai/images/edits, explicitly set model to gpt-image-2.5-flare, and submit a single image URL or an array of URLs through image. In the prompt, clearly describe what to preserve and what to change, for example, keep the product angle and outline while changing only the background and lighting.
The range for n is 1–10, making it suitable for generating alternatives around the same brief. If response_format=b64_json is selected, only 1 image is supported; use the url return method when multiple images are needed. Batch generation still requires checking each result; do not assume all images meet the same detail requirements.
Do not reuse it directly. The mask workflow should use the gpt-image-2.5-flare:official endpoint that supports this method, and upload the original image and Alpha PNG mask together via multipart. For basic Flare reference image editing, first use text to clearly specify the edit area; do not mix the two calling methods.
When exact pixels are required, write size as WIDTHxHEIGHT and comply with the dimension limits; when you only want to express composition intent, use auto. Long tasks can include callback_url: first save the returned task_id, then receive the completed result; callback handling should deduplicate by task ID to avoid duplicate database entries.
Choose a development approach or application suited to this model and follow its setup guide.
↗Python SDK Integration Guide
SDK installation, authentication and examples↗TypeScript SDK Integration Guide
SDK installation, authentication and examples
↗↗This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs