How to Use GPT Image 1.5 Edit in Muse
Use GPT Image 1.5 Edit to revise an existing image while preserving its subject, lighting, or composition. Unlike GPT Image 1.5, it starts with reference images for tasks such as background changes and targeted corrections.
Prompts to try with GPT Image 1.5 Edit in Muse
Copy an example into Muse, or ask in your own words.
Use GPT Image 1.5 Edit on the attached kettle photo. Change the setting to a kitchen table beside a rainy window, preserve the kettle's shape and finish, keep reference details closely, and make the result 1536×1024.
Use GPT Image 1.5 Edit on the attached portrait. Remove only the empty chair behind the person; preserve their face, clothing, pose, and the existing lighting. Return a 1024×1536 image.
Remove the background from the photo I attach with GPT Image 1.5 Edit and give me a transparent PNG.
Use GPT Image 1.5 Edit to clean up these product shots so they sit on pure white.
Edit this image with GPT Image 1.5 Edit: keep the subject, swap the background for a sunlit studio.
How to set up GPT Image 1.5 Edit in Muse
Pick the way that suits you. Each takes about two minutes.
Use the Muse connector
- Create an API key
Create one under API keys in the Spiral console.
- Send Muse this message
Muse reads Spiral's skill and asks for an API key.
set up https://spiral.ai/SKILL.md
- Give Muse the key
Paste the key when Muse asks for it, never in the chat itself.
Use the Spiral skill
- Send Muse 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 GPT Image 1.5 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/gpt-image-1.5/edit", "input": { "prompt": "Same workers, same beam, same lunch boxes - but they'\''re all on their phones now. One is taking a selfie. One is on a call looking annoyed. Same danger, new…", "image_urls": [ "<image_urls>" ] } }'
Then paste one of the prompts above: Muse finds GPT Image 1.5 Edit on Spiral, shows the price and runs it.
GPT Image 1.5 Edit providers and prices
Spiral runs GPT Image 1.5 Edit through fal. Open a card for today's price, with every fee included.
Up to $0.26 per run at the default inputs. quality: low $0.0169, medium $0.0663, high (default) $0.26. Per unit of num_images: low $0.0169, medium $0.0663, high (default) $0.26.
Settings you can ask for
GPT Image 1.5 Edit works from your prompt and image URLs. Ask Muse for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Image size | auto, 1024x1024, 1536x1024, or 1024x1536 | auto | Aspect ratio for the generated image |
| Background | auto, transparent, or opaque | auto | Background for the generated image |
| Quality | low, medium, or high | high | Quality for the generated image |
| Input fidelity | low or high | high | Input fidelity for the generated image |
| Number of images | 1 to 4 | 1 | Number of images to generate |
| Output format | jpeg, png, or webp | png | Output format for the images |
Every API field of GPT-Image 1.5 · Edit Image is on its tool page: open its card above.
What can you do with GPT Image 1.5 Edit in Muse?
Turn a creative brief into an illustration, poster, or labeled visual you can review in conversation. Specify the subject, composition, and exact wording before asking the agent to make the image.
Event poster concepts
Create a poster from a written brief with GPT Image 1.5, or revise an existing poster with GPT Image 1.5 Edit. Specify the exact headline, its position, and the main illustration.
Explainer infographics
Illustrate a short process with labeled panels. Use GPT Image 1.5 for the initial concept or GPT Image 1.5 Edit to revise a supplied diagram.
Editorial illustrations
Develop an illustration for an article or newsletter with GPT Image 1.5. Use GPT Image 1.5 Edit when the illustration already exists and needs a different treatment.
Product scene concepts
Explore materials, lighting, and staging before a photo shoot. Use GPT Image 1.5 for an imagined product scene or GPT Image 1.5 Edit to work from an approved product photo.
Seasonal photo treatments
Use GPT Image 1.5 Edit to change a supplied photo from a summer setting to a winter scene. State which subject details, camera angle, and composition should stay the same.
Targeted image corrections
Use GPT Image 1.5 Edit to remove a distracting object or change one visual detail in a supplied image. List the parts that should remain unchanged.
More on GPT Image 1.5 Edit and Muse
Overview
GPT Image 1.5 Edit in other agents
Questions about GPT Image 1.5 Edit in Muse
Can Muse use GPT Image 1.5 Edit?
Yes. Add Spiral to Muse as an MCP server, and Muse can find and run GPT Image 1.5 Edit like any built-in tool.
How much does GPT Image 1.5 Edit cost in Muse?
Up to $0.26 per run at the default inputs. `quality`: low $0.0169, medium $0.0663, high (default) $0.26. Per unit of `num_images`: low $0.0169, medium $0.0663, high (default) $0.26. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse plan is separate.
Do I need a fal account to use GPT Image 1.5 Edit in Muse?
You need no fal account. Muse uses one Spiral API key for every tool, and Spiral runs GPT Image 1.5 Edit on its own fal account.
How long does it take to set up GPT Image 1.5 Edit in Muse?
About two minutes: create an API key, then send Muse this message, then give Muse the key.
Does Muse wait while GPT Image 1.5 Edit runs?
GPT Image 1.5 Edit runs in the background. Muse starts the run, checks on it and gives you the image when it's ready.
What is GPT Image 1.5 useful for?
Use it for illustrations, product scene concepts, infographics, and posters with text inside the image. Describe the intended use and the visual details that matter, such as materials, lighting, and panel arrangement.
What image sizes does GPT Image 1.5 produce?
It produces 1024×1024 square images, 1536×1024 landscape images, and 1024×1536 portrait images. Choose the composition for its destination before generating the image.
How should I request text inside an image?
Put the exact wording in quotation marks and describe where it belongs. For example: Place "Saturday plant swap" at the top in large black lettering.
Can GPT Image 1.5 produce a transparent background?
Yes. Explicitly request a transparent background and choose PNG or WebP so the output can retain transparency.
How should I brief a photorealistic image?
Describe the subject, materials, and lighting in concrete terms. A request for a brushed steel kettle beside a window gives a clearer target than a request for a beautiful product image.
Start using GPT Image 1.5 Edit in Muse
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse:
set up https://spiral.ai/SKILL.md


