Spiral gives your agent every tool with one account. Browse the tools →

ChatGPT · ImageReleased 2026-03-26

How to Use Phota Image Editing in ChatGPT

Phota Image Editing changes poses, expressions, lighting, and backgrounds in existing photos while using trained profiles to preserve likeness. Unlike Phota Text to Image, it starts with a photo whose composition you can retain or reshape.

Prompts to try with Phota Image Editing in ChatGPT

Copy an example into ChatGPT, or ask in your own words.

Use Phota Image Editing on this attached portrait with my matching saved profile. Turn my gaze toward the camera and keep my clothing, hairstyle, background, and lighting unchanged.

Phota Image EditingChatGPT
Try asking
  • Use Phota Image Editing to combine these two attached portraits into one group photo. Use the matching saved profiles, put both people at the same distance from the camera, and match the lighting.

  • Remove the background from the photo I attach with Phota Image Editing and give me a transparent PNG.

  • Use Phota Image Editing to clean up these product shots so they sit on pure white.

  • Edit this image with Phota Image Editing: keep the subject, swap the background for a sunlit studio.

How to set up Phota Image Editing in ChatGPT

Pick the way that suits you. Each takes about two minutes.

Use the ChatGPT connector

  1. 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
  2. Click Connect

    ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

  3. 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

  1. Send ChatGPT this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. 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

  1. Create an API key

    In the console, under API keys.

  2. Run Phota Image Editing

    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/phota/edit",
        "input": {
          "prompt": "Make this scene more realistic but still keep the game vibes",
          "image_urls": [
            "<image_urls>"
          ]
        }
      }'

Then paste one of the prompts above: ChatGPT finds Phota Image Editing on Spiral, shows the price and runs it.

Phota Image Editing providers and prices

Spiral runs Phota Image Editing through fal. Open a card for today's price, with every fee included.

falImage
Phota · Image Editing
fal-ai/phota/edit

Settings you can ask for

Phota Image Editing works from your prompt and image URLs. Ask ChatGPT for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Number of images1 to 41

Number of images to generate.

Output formatjpeg or pngjpeg

The format of the generated image.

Resolution1K or 4K1K

Resolution of the generated image.

Aspect ratioauto, 1:1, 16:9, 4:3, 3:4, or 9:16auto

Aspect ratio of the generated image.

Base modelnb2, qwen-image-2, flux-2, or seedream-5-pronb2

Base model used to render the image. Identity composes on top of whichever base model is selected, so trained profiles work with all of them. Only nb2 supports 4K.

Every API field of Phota · Image Editing is on its tool page: open its card above.

What can you do with Phota Image Editing in ChatGPT?

Turn a visual idea into portraits, themed scenes, or campaign images featuring recognizable people. A chat app can help specify the framing and lighting, then compare candidates with you.

Matching team headshots

Create portraits with the same framing, background, and lighting for a team page. Use each person's trained profile and repeat the photographic direction.

Profile portraits

Make a recognizable portrait for a speaker bio or social profile, with a setting and expression chosen for the intended audience.

Seasonal cards

Create holiday portraits featuring known people or pets, with coordinated clothing, lighting, and scenery.

Campaign photo sets

Carry the same recognizable person through several campaign scenes. Keep the cast and photographic direction consistent while changing the setting.

Storyboard images

Build individual shots for a storyboard with a recurring cast. Specify each character's position, expression, and action in every scene.

Keyframes for video

Create still start and end frames featuring the same person for a separate image-to-video model.

Expression corrections

Start with an existing portrait and adjust the subject's expression or gaze while requesting that the outfit, background, and lighting remain unchanged.

Combined group portraits

Bring people from separate photos into one group portrait. Reference the relevant profiles and specify placement, shared lighting, and camera perspective.

Questions about Phota Image Editing in ChatGPT

Can ChatGPT use Phota Image Editing?

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Phota Image Editing like any built-in tool.

How much does Phota Image Editing cost in ChatGPT?

$0.117 per run at the default inputs. `resolution`: 1K (default) $0.117, 4K $0.234. $0.117 per unit of `num_images`. 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 Phota Image Editing in ChatGPT?

No. Spiral runs Phota Image Editing on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up Phota Image Editing in ChatGPT?

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

Does ChatGPT wait while Phota Image Editing runs?

Phota Image Editing runs in the background. ChatGPT starts the run, checks on it and gives you the image when it's ready.

What is Phota best at?

Phota is built for portraits and scenes where a specific person should remain recognizable. Useful applications include headshots, themed photo sets, campaign images, and storyboards with a recurring cast.

Why might a Phota portrait look like a different person?

Phota needs the correct trained profile referenced in the request to preserve a specific person's likeness. Clear profile photos with varied angles and expressions also matter.

Can Phota keep someone recognizable across different scenes?

That is Phota's main purpose. A trained profile carries the person's appearance across changes in setting, clothing, and photographic style.

How should I write a Phota prompt?

Describe the subject, framing, pose, expression, setting, and lighting. State which details must stay the same, especially when changing an existing composition.

Can Phota produce 4K images?

Yes. For these Phota models, choose Nano Banana 2 when requesting 4K output.

Get started

Start using Phota Image Editing in ChatGPT

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into ChatGPT:

Set up ChatGPT

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options