How to Use Face Enhancement in Amp
Face Enhancement retouches facial features in an existing photo with a natural-looking finish. Use it for headshots, speaker portraits, and profile photos that need facial retouching.
Prompts to try with Face Enhancement in Amp
Copy an example into Amp, or ask in your own words.
Use Face Enhancement on the staff headshots in this project's assets directory with 30 sampling steps. Save separate edited copies and build a page showing each original beside its result.
Use Face Enhancement on the author portrait used by this site's biography page. Add an original-versus-edited preview so I can choose which image to use.
Use Face Enhancement on the speaker portraits referenced by the event data. Keep each result linked to its original speaker record and prepare a review gallery.
Use Face Enhancement on the podcast guest headshots in this project. Record the returned pixel dimensions and flag images that are too small for our existing portrait layout.
Use Face Enhancement on one portrait from this project's sample images with 30 sampling steps. Show it beside the original at the same display size for a facial detail review.
How to set up Face Enhancement in Amp
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
No header and no client ID or secret: Amp registers itself with Spiral.
amp mcp add spiral https://api.spiral.ai/mcp
- Sign in
Start amp. Amp opens Spiral's sign-in page in your browser: sign in, pick the organization and click Authorize. No API key.
- Check it
amp mcp doctor
Use the Spiral skill
- Send Amp 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 Face Enhancement
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/image-editing/face-enhancement", "input": { "image_url": "https://v3.fal.media/files/zebra/hAjCkcyly4gsS9-cptD3Y_image%20(20).png" } }'
Then paste one of the prompts above: Amp finds Face Enhancement on Spiral, shows the price and runs it.
Face Enhancement providers and prices
Spiral runs Face Enhancement through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Face Enhancement works from your image URL. Ask Amp for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Guidance scale | 0 to 20 | 3.5 | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
| Number of inference steps | 1 to 50 | 30 | Number of inference steps for sampling. |
| Safety tolerance | 1 to 6 | 2 | The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive. |
| Output format | jpeg or png | jpeg | The format of the generated image. |
| Aspect ratio | 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16 and 1 more | The aspect ratio of the generated image. | |
| Seed | a whole number | The same seed and the same prompt given to the same version of the model will output the same image every time. |
Every API field of Image Editing Face Enhancement is on its tool page: open its card above.
What can you do with Face Enhancement in Amp?
Prepare retouched portraits for staff directories, author pages, and speaker sections using Face Enhancement. A coding agent can work from project images and build a comparison view for review.
Staff directory portraits
Retouch existing employee headshots, then review each result beside its original before updating the directory.
Conference speaker photos
Prepare submitted speaker portraits for event pages, keeping the original available for comparison.
Professional profile pictures
Try facial retouching on a current profile photo and choose the result that still looks like you.
Author portraits
Retouch an existing author headshot for a biography page or article byline.
Podcast guest portraits
Prepare guest headshots for episode pages and compare facial appearance before using the edited images.
Portrait client previews
Create a facial retouching preview from a selected portrait so the client can compare it with the original.
More on Face Enhancement and Amp
Overview
Face Enhancement in other agents
Questions about Face Enhancement in Amp
Can Amp use Face Enhancement?
Yes. Add Spiral to Amp as an MCP server, and Amp can find and run Face Enhancement like any built-in tool.
How much does Face Enhancement cost in Amp?
$0.052 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Amp plan is separate.
Do I need a fal account to use Face Enhancement in Amp?
No. Spiral runs Face Enhancement on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Face Enhancement in Amp?
About two minutes: add the server, then sign in, then check it.
Does Amp wait while Face Enhancement runs?
Face Enhancement runs in the background. Amp starts the run, checks on it and gives you the image when it's ready.
What is Face Enhancement best used for?
It targets facial retouching with a natural-looking finish. Consider it for existing headshots, profile pictures, and speaker portraits.
Can I describe exactly which facial features to change?
The documented schema has no custom text prompt. Tell your agent what to check in the result, but do not expect written instructions to become precise facial editing controls.
Does Face Enhancement guarantee that the person will look identical?
fal describes a natural, realistic finish without promising exact identity preservation. Compare the result with the original before choosing it for a portrait.
What resolution does Face Enhancement produce?
The official documentation does not specify a fixed output resolution or maximum pixel size. Check the returned image dimensions before planning a crop or print.
Will more sampling steps produce a better face?
The documented default is 30 steps, with no published guarantee that more steps improve facial fidelity. Start there and compare results before changing the setting.
Start using Face Enhancement in Amp
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Amp:
set up https://spiral.ai/SKILL.md


