GPT Image 2.5 Sunburst for Image Edit

ABOUT THE WORKFLOW

Edit an Image Upload an image and describe the change you want. GPT Image 2.5 Sunburst reads the image, applies your edit, and returns the result. Add a second reference image to guide the edit. That's it.

Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.

Model

• GPT Image 2.5 Sunburst by OpenAI. The precision tier of the GPT Image 2.5 series, built for tight editing control and subject consistency across changes.

HOW IT WORKS

Step 1. Upload your image The image you want to edit. Any photo, render, or screenshot works. Works great with: photos · product shots · portraits · designs

Step 2. Describe the change Say what to change in plain language. "Make the sky orange and keep the building the same" is better than "improve the image."

Step 3. Add a reference image (optional) Upload a second image to guide the edit. Use it to bring in a style, a colour palette, or a specific object. The model accepts up to 16 images total if you wire more inputs.

Step 4. Hit run and download Sunburst applies the edit and returns the result as a preview. Right-click the preview to save, or add a SaveImage node for automatic downloads. Ready for: Photoshop · Figma · Canva · any editor

First time? Leave every setting as-is. The defaults (1 image · high quality · PNG) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard edit (most people) — 1 image · high quality · PNG · auto size. The right starting point for almost everyone.

• Want options to choose from — Raise the number of images to generate several edited versions and keep the strongest. Both quality and image count drive cost.

• Need a transparent background — Set background to "transparent" instead of "auto." Use PNG output to preserve the alpha channel.

• Working on a hero image or campaign asset — Set quality to "xhigh" or "max" for finer detail. Expect longer generation times and higher cost per run.

• Quick test before committing — Set quality to "low" or "medium" for a fast preview. Switch to "high" or above for the final version.

• The edit is drifting from your original — Name what to keep in the prompt, not only what to change. "Change the background to a beach. Keep the person and their outfit the same." beats "put them on a beach."

• Need a different file type — Switch output format to match where the image is going.

Prompt: Be specific about what to change and what to preserve. "Swap the background to a sunset beach, keep the subject and lighting the same" is clearer than "make it look better." If the model changes something you wanted to keep, tell it to leave that part alone.

LEARN

📹 Videos

• Intro to Floyo

• ComfyUI 101 Free Course ft. Sebastian Kamph

• Floyo 101 for Team Collaboration

✨ Quick links

• Help docs

• LoRA Training guide

• Discover more workflows

USE CASES

🎨 Style Changes & Restyling Restyle a photo into a new art style, era, or visual treatment from a single instruction. Add a reference image to match a specific look.

🖼️ Background & Object Edits Swap backgrounds, add or remove objects, and change specific details in a shot while the subject stays recognizable.

🛍️ Product & Marketing Visuals Adjust product shots for new campaigns, swap environments, or recolour elements. The model keeps the product intact across changes.

📸 Portrait & Headshot Editing Change outfits, lighting, or backgrounds on portraits. Sunburst holds facial features and fine details steady through edits.

🔤 Text-in-Image Edits Add, replace, or correct text inside an image. Sunburst renders legible type, which most image models struggle with.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Clear, specific edit instructions

• Single, well-lit source images

• Naming what to keep and what to change

• Reference images to guide the look

• Edits that add or change legible text

⚠️ May produce softer results

• Vague prompts like "make it better" or "improve this"

• Crowded source images with too many subjects

• Conflicting instructions in one prompt

• Expecting instant results at max quality (Sunburst trades speed for precision)

FAQ

What is GPT Image 2.5 Sunburst? GPT Image 2.5 Sunburst is the precision tier of OpenAI's GPT Image 2.5 series, released September 8, 2026. It is built for detailed creative and editing work where accuracy matters more than speed. It accepts text prompts and up to 16 reference images per request and outputs from 1024px up to 4K.

How is GPT Image 2.5 Sunburst different from Flare? Flare is the faster, lighter variant designed for everyday generation and high-volume work. Sunburst takes longer to generate but gives tighter control over edits, with stronger subject consistency across changes. For quick iterations and moodboards, start with Flare. For final campaign assets and precise retouching, use Sunburst.

What quality setting should I use for GPT Image 2.5 Sunburst edits? Start with "high," the default. It covers most use cases. Step up to "xhigh" or "max" when fine detail matters, such as product photography or print assets. Both higher tiers cost more per run and take longer. Use "low" or "medium" for fast previews before committing.

Can I use GPT Image 2.5 Sunburst outputs commercially? GPT Image 2.5 Sunburst is a proprietary OpenAI model, so commercial use is governed by OpenAI's usage policies rather than an open license. Commercial use is generally allowed under those terms. Review OpenAI's current policies for your specific use case, and make sure you have the rights to any source image you upload.

Can GPT Image 2.5 Sunburst edit or add text inside an image? Yes. Accurate text rendering is one of the strengths of the GPT Image 2.5 series. Spell out the exact words you want in your prompt. This makes it a good fit for editing signs, labels, packaging, or titles within an image.

Does GPT Image 2.5 Sunburst support transparent backgrounds? Yes. Set the background option to "transparent" and use PNG as the output format. This gives you a cutout you can composite in Photoshop, Figma, or any editor that supports alpha channels.

How to run GPT Image 2.5 Sunburst online? You can run GPT Image 2.5 Sunburst online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, upload an image, describe the edit, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A designer runs an edit and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it? Upload an image, describe the change, and run it. The settings are already set.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.