Create portraits

POST/images/edits

Makes portraits with PhotoMaker V2 from 1 to 4 face photos and a prompt that holds the trigger word img right after the subject. Same key and credit as chat; billed per second of generation.

Catalogue checked on 20 Oct 2026

SoonOpening soon: what follows describes the service as it will work.

Server URLhttps://evanesca.app/api/v1

POST/images/editsOpens at launch

AuthorizationBearer $EVANESCA_API_KEY

Headers

Authorizationstringrequired
Bearer followed by your key, which starts with sk-eva-.
Content-Typestringrequired
Multipart, as OpenAI's contract has it — or JSON, with the photos as data URLs.
Valuesmultipart/form-dataapplication/json

Request body

multipart/form-data

modelstringrequired
PhotoMaker V2, by TencentARC.
Valuesphotomaker-v2
promptstringrequired
350 characters at most, with the trigger word img right after the subject: “a woman img as an astronaut”.
image[]filerequired
1 to 4 face photos, JPEG or PNG, one field per photo.
imagesarray of strings
In a JSON body, instead of image[]: the photos as base64 data URLs.
ninteger
How many images to make.
Default1
Values1–5
sizestring
The size of each image, in pixels.
Default1024x1024
Values1024x10241792x10241024x1792

Where it runs, what it costs

Evanesca · on the record

Runs in: Infomaniak · Switzerlandphotomaker-v2
Operator keeps: Infomaniak states that queries are “neither recorded nor used to train models” (Infomaniak AI Tools).
Costs: €0.0092 per second of generation, VAT included, rounded up to the next second, one second at least; usage.generation_seconds is what is billed. About 5 seconds, so about €0.05, for a typical PhotoMaker V2 portrait. A refused request costs nothing.
Response headers: x-evanesca-operator: infomaniak
x-evanesca-location: switzerland

The prompt and the face photos go to Infomaniak, in Switzerland — outside the EU, under an EU adequacy decision; the images come back in the response and Evanesca keeps none of them. The images carry IPTC metadata marking them as AI-generated (AI Act, art. 50(2)) — metadata, not a watermark, so a screenshot or a re-encode can remove it (Images).

A face photo is personal data: send only photos you are allowed to use. The terms forbid an image of a real person without their consent, and any sexual or intimate image of a real person, even with their consent.

Errors

Status	type	Meaning
400	`invalid_request`	A prompt without img or over 350 characters, no photo or more than 4, a file that is neither JPEG nor PNG, n or size out of bounds — the param field says which (limits).
401	`invalid_api_key`	No key, a malformed key, or a revoked one.
402	`insufficient_credit`	Your credit is at zero or below. Add credit to continue.
404	`model_not_found`	Unknown ID, a model Evanesca does not serve, or flux-schnell, which is served by /images/generations.
502	`upstream_error`	The operator could not be reached, sent an unreadable answer, or turned down Evanesca's own account. Your key is not the problem: retry.

Other operator errors reach you with its status and body, and Retry-After when it sends one (errors).

curl https://evanesca.app/api/v1/images/edits \
  -H "Authorization: Bearer $EVANESCA_API_KEY" \
  -F model=photomaker-v2 \
  -F "prompt=a woman img as an astronaut" \
  -F "image[]=@face-1.jpg" \
  -F "image[]=@face-2.jpg"

import os
import requests

res = requests.post(
    "https://evanesca.app/api/v1/images/edits",
    headers={"Authorization": f"Bearer {os.environ['EVANESCA_API_KEY']}"},
    data={"model": "photomaker-v2", "prompt": "a woman img as an astronaut"},
    files=[
        ("image[]", open("face-1.jpg", "rb")),
        ("image[]", open("face-2.jpg", "rb")),
    ],
)
print(res.status_code, res.json()["usage"])

import { readFile } from "node:fs/promises";

const form = new FormData();
form.append("model", "photomaker-v2");
form.append("prompt", "a woman img as an astronaut");
for (const name of ["face-1.jpg", "face-2.jpg"]) {
  form.append("image[]", new Blob([await readFile(name)], { type: "image/jpeg" }), name);
}

const res = await fetch("https://evanesca.app/api/v1/images/edits", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.EVANESCA_API_KEY}` },
  body: form,
});
console.log(res.status, (await res.json()).usage);

{
  "created": 1791763200,
  "model": "photomaker-v2",
  "data": [{ "b64_json": "/9j/4AAQSkZJRgABAQ…" }],
  "usage": { "generation_seconds": 5, "images": 1 }
}

{
  "error": {
    "message": "\"photomaker-v2\" needs the trigger word \"img\" right after the subject in the prompt, e.g. \"a woman img as an astronaut\". Nothing was charged.",
    "type": "invalid_request",
    "param": "prompt"
  }
}

Create portraits

Headers

Request body

Where it runs, what it costs

What leaves Evanesca

Errors