Flare / Sunburst
Sunburst focuses on edit fidelity. Use it when preserving the reference matters most.
GPT Image 2.5
Create and edit images with GPT Image 2.5.
Image models you can open next
Explore other image models for generation and editing.
GPT Image 2.5
Create a new image. Refine the details that matter.
Begin from a written brief or work from your own stills. GPT Image 2.5 combines image generation and guide editing in one workspace, with Flare for faster iteration and Sunburst for edits where fidelity matters. Without switching pages, pick the version for each task.
Flare / Sunburst1K / 2K / 4KEdit a region with a mask
Low → Maximum
Five quality levels let you balance detail, generation time plus credits.
1–10
Choose 1–10 images per request. After completion, pick each thumbnail to preview and download that image. After leaving the page, your results remain accessible from Library.
From a first draft to a focused edit
Before making as many as 10 images, render and edit images with GPT Image 2.5. Pick Flare or Sunburst, add guides and masks, set dimensions, and review credits.
Build the scene from a clear brief
Describe the subject, setting, lighting and composition. For a poster or interface concept, put the exact words in quotation marks plus specify their placement. Review the output for spelling, anatomy and product accuracy.
Guide changes with your reference images
Add as many as 16 stills, sketches or layout guides. Explain what each guide contributes and name what should remain unchanged. A guide guides the output; it does not guarantee an exact match.
Edit a region with a mask
Upload a PNG matching the first guide image’s dimensions. Transparent pixels mark this area to change; opaque pixels mark the area to preserve.
Size mode
Width and height has to be multiples of 16, with no more than 3,840 px per side, 655,360–8,294,400 total pixels and an aspect ratio no wider than 3:1.
Transparent · Preview
Transparent output is a preview feature. Before relying on the image, inspect the alpha channel and edges.
Compare up to 10 outputs
Choose 1–10 images per request. After completion, pick each thumbnail to preview and download that image. After leaving the page, your results remain accessible from Library.
See the model at work
Explore examples of scene generation and reference editing. These samples show sample outputs; they are not VoraVideo scorecards.
A dense city shot with a steady visual direction
This Flare sample combines a neon city, people, architecture and night light. Use a similarly structured brief to establish the shot first, then refine individual fine points.
Flare
Flare is the faster choice for everyday generation plus editing.
Change the clothing while keeping the portrait recognizable
OpenAI’s published comparison changes one red shirt into formalwear. Move the divider to compare the source plus edited portrait. This demonstrates Images 2.5; the example does not identify a particular API subversion.
Guide changes with your reference images
Add as many as 16 stills, sketches or layout guides. Explain what each guide contributes and name what should remain unchanged. A guide guides the output; it does not guarantee an exact match.
How to use GPT Image 2.5
01
Choose a version and input mode
Begin with Flare for iteration or Sunburst for precise edits. Pick text-to-image for a new shot, or image-to-image to upload guides.
02
Set the output and check the quote
Choose quality, size, background and image count. For local edits, add an alpha mask matching the first guide. The button shows the total credits before submission.
03
Generate, compare and download
Wait for completion, inspect every output and download the ones you need. To refine a output, upload it as the guide for a new request.
FAQ
GPT Image 2.5 · FAQ
What is the difference between Flare and Sunburst?
Flare is the faster choice for everyday generation plus editing. Sunburst focuses on edit fidelity. Use it when preserving the reference matters most.
Can I edit only part of an image?
Upload a PNG matching the first guide image’s dimensions. Transparent pixels mark this area to change; opaque pixels mark the area to preserve.
What does 4K mean on this page?
Output above 3,686,400 pixels is experimental. The 4K label is one pixel budget: 16:9 reaches 3840×2160; square output is 2880×2880.
Can I generate several images at once?
Choose 1–10 images per request. After completion, pick each thumbnail to preview and download that image. After leaving the page, your results remain accessible from Library.
How are VoraVideo credits calculated?
Credits depend on quality, output dimensions, prompt length, guide images, masks and image count. The generation button shows this quote for your current settings before submission. Review it after changing the inputs; each new generation relies on credits.
Is this the same as ChatGPT Images?
This page provides image generation plus editing in VoraVideo. ChatGPT-specific Drawing, image comments and conversational history are not part of this API path. You can supply your own drawing as a guide or upload a downloaded output for another edit.
Make your next image with GPT Image 2.5
Begin with a prompt, pick your version and review the credits before rendering.