How to Use Gemini 2.5 Flash Image Edit in ChatGPT
Gemini 2.5 Flash Image Edit changes existing pictures with written instructions, including backgrounds, colors, and visual styles. Unlike Gemini 2.5 Flash Image, it uses image references to guide the result and preserve the subject.
Prompts to try with Gemini 2.5 Flash Image Edit in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use Gemini 2.5 Flash Image Edit on the attached mug photo. Place it on a breakfast table beside a window, preserving the mug's handle, glaze, and proportions. Make the picture square.
Use Gemini 2.5 Flash Image Edit to turn the attached street photograph into an ink-and-wash illustration. Preserve the arrangement of the buildings and people, and keep the original proportions.
Remove the background from the photo I attach with Gemini 2.5 Flash Image Edit and give me a transparent PNG.
Use Gemini 2.5 Flash Image Edit to clean up these product shots so they sit on pure white.
Edit this image with Gemini 2.5 Flash Image Edit: keep the subject, swap the background for a sunlit studio.
How to set up Gemini 2.5 Flash Image Edit in ChatGPT
Pick the way that suits you. Each takes about two minutes.
Use the ChatGPT connector
- Add a custom MCP server
In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.
https://api.spiral.ai/mcp
- Click Connect
ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.
- Sign in to Spiral and approve
Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.
Use the Spiral skill
- Send ChatGPT this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Gemini 2.5 Flash Image Edit
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "fal", "model": "fal-ai/gemini-25-flash-image/edit", "input": { "prompt": "make a photo of the man driving the car down the california coastline", "image_urls": [ "<image_urls>" ] } }'
Then paste one of the prompts above: ChatGPT finds Gemini 2.5 Flash Image Edit on Spiral, shows the price and runs it.
Gemini 2.5 Flash Image Edit providers and prices
Spiral runs Gemini 2.5 Flash Image Edit through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Gemini 2.5 Flash Image Edit works from your prompt and image URLs. Ask ChatGPT for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Number of images | 1 to 4 | 1 | The number of images to generate. |
| Seed | a whole number | The seed for the random number generator. | |
| Aspect ratio | auto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5 and 3 more | auto | The aspect ratio of the generated image. |
| Output format | jpeg, png, or webp | png | The format of the generated image. |
| Safety tolerance | 1 to 6 | 4 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. |
| Limit generations | on or off | on | Experimental parameter to limit the number of generations from each round of prompting to 1. Set to |
Every API field of Gemini 2.5 Flash Image · Image Editing is on its tool page: open its card above.
What can you do with Gemini 2.5 Flash Image Edit in ChatGPT?
Turn a written idea into artwork you can review in conversation. Use the chat to make the subject, setting, and composition explicit before requesting an image with Gemini 2.5 Flash Image.
Article illustrations
Illustrate an article's main idea from a written brief, or adapt an existing illustration with Gemini 2.5 Flash Image Edit. Leave space for the headline to be added separately.
Product scene concepts
Explore a product scene from a description. Use Gemini 2.5 Flash Image Edit when the concept needs to start with an actual product photo, then inspect identifying details.
Social post artwork
Create a scene for a portrait or square post, or revise existing artwork with Gemini 2.5 Flash Image Edit. Keep the caption outside the generated picture when exact wording matters.
Packaging concepts
Explore package shapes, materials, and visual treatments before production design. Start from a description or use Gemini 2.5 Flash Image Edit to revise a photographed mockup.
Story scene development
Develop illustrated scenes with explicit character and style descriptions. Use Gemini 2.5 Flash Image Edit when a previous picture should guide the character's appearance.
Website artwork
Create landscape artwork for an article header or landing page, or revise an existing asset with Gemini 2.5 Flash Image Edit. Describe where the subject should sit relative to the page's text.
Background replacement
Use an existing product or portrait image and request a different setting while preserving the subject. Specify the parts that should remain unchanged.
Illustrated treatments of photographs
Turn an existing photograph into a watercolor, ink drawing, or another described visual style. State which composition and subject details should carry over.
More on Gemini 2.5 Flash Image Edit and ChatGPT
Overview
Gemini 2.5 Flash Image Edit in other agents
Questions about Gemini 2.5 Flash Image Edit in ChatGPT
Can ChatGPT use Gemini 2.5 Flash Image Edit?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Gemini 2.5 Flash Image Edit like any built-in tool.
How much does Gemini 2.5 Flash Image Edit cost in ChatGPT?
$0.05174 per image. Billed on `num_images`, default 1. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.
Do I need a fal account to use Gemini 2.5 Flash Image Edit in ChatGPT?
No. Spiral runs Gemini 2.5 Flash Image Edit on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Gemini 2.5 Flash Image Edit in ChatGPT?
About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.
Does ChatGPT wait while Gemini 2.5 Flash Image Edit runs?
Gemini 2.5 Flash Image Edit runs in the background. ChatGPT starts the run, checks on it and gives you the image when it's ready.
What is Gemini 2.5 Flash Image useful for?
Use it for illustrations, product concepts, editorial scenes, and related visual assets. Describe the subject, setting, and intended appearance in a clear brief.
How should I write a Gemini 2.5 Flash Image prompt?
Describe one coherent scene in sentences: who or what appears, where it sits, and how it should look. For example, describe a ceramic mug beside a window in soft morning light instead of listing unrelated style words.
Can I rely on text inside the image?
Proofread it before use, especially when it contains several sentences or small lettering. Google lists long-form text rendering as a known weakness; for text-heavy designs, consider adding the final copy in a design editor.
What dimensions does Gemini 2.5 Flash Image produce?
Google documents 1344 × 768 pixels for a 16:9 landscape image, 768 × 1344 for a 9:16 portrait image, and 1536 × 672 for a 21:9 image. Choose the composition around its final placement.
Should I check small details before publishing?
Yes. Google identifies factual representation of fine details as a limitation, so inspect any detail that carries meaning, such as a product feature or a diagram label.
Start using Gemini 2.5 Flash Image Edit in ChatGPT
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into ChatGPT:
set up https://spiral.ai/SKILL.md


