Flare
A practical default for concept rounds, social assets, visual prototypes, and other latency-sensitive work.
Preview
Explore another image workflow
Compare image models when you need a different balance of speed, edit control, style, or output cost.
GPT Image 2.5 in AI Image Editor
Choose speed for the draft or control for the revision
This workspace exposes both GPT Image 2.5 API models. Flare is tuned for fast, high-quality everyday generation, while Sunburst is intended for jobs where the details surrounding an edit need closer control. Both can start from text or images.
Flare for rapid iterationSunburst for precise editsText, references, mask, and alpha output
Sunburst
Choose it when a product, person, layout, or surrounding scene must remain more controlled through an edit.
One stored image
Each submission returns one result to your generation history for review and download.
Built for visual work that cannot afford accidental changes
GPT Image 2.5 adds useful control at each stage: define the deliverable, assign roles to references, limit the edit area, and select output settings before the request runs.
Carry a subject into a new scene
Use a portrait or product reference to explore a different setting, composition, or visual treatment while asking the model to retain recognizable details.
Give every reference a job
Upload up to 16 JPEG, PNG, or WebP files and state which image supplies the subject, lighting, palette, pose, layout, or material cues.
Protect the untouched area
Add a same-size PNG mask to the first reference. Transparent mask pixels mark the region to revise; opaque pixels identify what should stay protected.
Produce assets with real alpha
Select transparent background for cutouts, stickers, interface pieces, or sprites, then inspect the downloaded PNG for halos and stray opaque pixels.
Frame output for its destination
Select from 15 aspect ratios, automatic sizing, or valid custom pixel dimensions. Ratio mode also offers 1K, 2K, and 4K resolution tiers.
Spend quality where viewers will notice
Move from Low through Maximum quality when dense text, small product details, or final-publish polish justify the added credits.
Three workflows that benefit from the two-model choice
Treat Flare and Sunburst as different production paths rather than a simple quality toggle. The right option depends on whether speed or edit precision carries more risk for the asset.
Frame a high-energy campaign moment
Use Flare to explore action-led ads, sports covers, social posts, or launch visuals when quick iteration matters.
Prompt by deliverable
Name the asset type and publishing context first, then describe the visible subject, hierarchy, lighting, palette, copy, and exclusions.
Move a familiar character into a new action
Use Sunburst when changing a pose, costume detail, or setting while the character’s face, proportions, palette, and design language need careful preservation.
Lock the identity before the edit
List the face, silhouette, costume, colors, scale, camera angle, and other elements that must survive the requested change.
Build a consistent character motion sheet
Generate a grid of related poses while keeping the character’s costume, proportions, camera, and rendering style aligned from cell to cell.
Check continuity across every cell
Review the face, hands, accessories, weapon, spacing, and action sequence before separating the sheet into individual frames.
Set up a GPT Image 2.5 request
01
Match the model to the cost of a mistake
Start with Flare when turnaround matters most. Switch to Sunburst when unintended changes to identity, layout, typography, or product detail would be expensive to correct.
02
Describe the visible result and the boundaries
Name the deliverable, assign a role to each reference, quote required on-image text, and spell out both what should change and what must remain untouched.
03
Choose output controls and review the actual file
Set quality, ratio or dimensions, resolution, and background. Check the credit estimate, generate, then inspect text, anatomy, identity, edges, and transparency before use.
Questions before you generate with GPT Image 2.5
When should I choose Flare instead of Sunburst?
Flare is the faster default for everyday creation and high-volume iteration. Sunburst is aimed at detailed creative work where tighter editing control matters more than turnaround time.
What can I use as a reference?
Image-to-image mode accepts up to 16 JPEG, PNG, or WebP references. Number them in the prompt and explain the role of each file instead of expecting the model to infer your intent.
What does the mask control?
The optional mask must be a PNG with the same dimensions as the first reference. Transparent mask pixels indicate where edits are allowed; opaque pixels indicate the area to preserve.
How do I request a transparent image?
Choose Transparent in the Background control. Also describe the intended cutout and edge treatment in the prompt, then verify the downloaded PNG alpha channel before production use.
Which size and quality options are available here?
You can use automatic sizing, one of 15 ratios, or valid custom dimensions. Ratio mode supports 1K, 2K, and 4K tiers, and quality ranges from Low to Maximum. The button shows the current credit estimate.
Does a reference guarantee exact identity, text, or product details?
No. References and preservation instructions improve control but do not guarantee an exact match. Review faces, hands, spelling, logos, geometry, claims, and rights before publishing.
Turn the next visual brief into a reviewable file
Pick the production path, define what may change, and generate one image with controls that match its destination.
Flare or Sunburst Model pathText + up to 16 images Inputs