# IP Adapter Face ID API

> Génère des images correspondant à un visage à partir d’une photo ou d’une archive zip de photos, sur des bases SD 1.5 ou SDXL

Personnalise la génération à partir d’un visage fourni via `face_image_url`, ou d’une archive zip de plusieurs visages via `face_images_data_url`, dont les plongements sont moyennés. `model_type` sélectionne des variantes SD 1.5 et SDXL, et les points de contrôle de base peuvent être modifiés avec les paramètres du dépôt. `width` et `height` vont de 512 à 1024, et `num_inference_steps` jusqu’à 200.

- Model id: `ip-adapter-face-id`
- Made by: Tencent
- Category: Image Editing
- Output: image
- Estimated price per run: $0.015 / image (cheapest run $0.06 (60 API credits))
- Run: `POST https://api.doitong.com/v1/run/ip-adapter-face-id`
- Quote: `POST https://api.doitong.com/v1/quote/ip-adapter-face-id`
- Docs page: https://doitong.com/fr-CA/developers/models/ip-adapter-face-id

## Pricing

Price: **$0.015 / image**. Estimated from the typical cost of one run, per output (`num_samples`). The quote is exactly what the run charges.

The full example input below costs $0.06 = 60 API credits (4 images × 15 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/ip-adapter-face-id` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `model_type` |  | enum (string) | no | `1_5-v1` | `1_5-v1`, `1_5-v1-plus`, `1_5-v2-plus`, `SDXL-v1`, `SDXL-v2-plus`, `1_5-auraface-v1` | Sélection du modèle, où 1_5 est la valeur par défaut et le choix recommandé pour la plupart des utilisations. |
| `prompt` |  | string | yes |  |  | Décrivez l’image que vous souhaitez générer avec le plus de détails possible pour obtenir les meilleurs résultats. |
| `face_image_url` |  | string (image URL) \| null | no |  |  | Image de référence pour la correspondance faciale, mise à l’échelle et rognée à 640x640 lorsque ses dimensions diffèrent. |
| `face_images_data_url` |  | string \| null | no |  |  | URL de l’archive zip d’images faciales, utilisée pour créer un identifiant facial plus précis en moyennant les représentations vectorielles des images archivées. |
| `negative_prompt` |  | string | no | `blurry, low resolution, bad, ugly, low quality, pixelated, interpolated, compression artifacts, noisey, grainy` |  | Invite négative indiquant les détails d’image indésirables. Elle peut exclure les couleurs, les objets, le décor ou des caractéristiques et qualités plus fines, comme une moustache, du flou ou une faible résolution. |
| `seed` |  | integer \| null | no |  |  | Graine pour reproduire des images dans Stable Diffusion. Une image peut être reproduite exactement à chaque exécution en conservant la version du modèle, l’invite et la graine inchangées. |
| `guidance_scale` |  | number | no | `7.5` | 0 – 16 | Intensité d’adhésion à l’invite pour la sélection d’images, exprimée comme CFG (Classifier Free Guidance). |
| `num_inference_steps` |  | integer | no | `50` | 1 – 200 | Nombre d’étapes d’inférence pour la génération d’image; des valeurs plus élevées améliorent la qualité de l’image au prix d’un temps de génération plus long. |
| `num_samples` |  | integer | no | `4` | 1 – 4 | Nombre d’échantillons pour l’identifiant facial, par défaut à 4. L’augmenter améliore la qualité de l’image, mais prolonge le temps de génération. |
| `width` |  | integer | no | `512` | 512 – 1,024 | Largeur de l’image obtenue. |
| `height` |  | integer | no | `512` | 512 – 1,024 | Hauteur de l’image obtenue. |
| `face_id_det_size` |  | integer | no | `640` | 64 – 640 | Définit la taille du modèle de détection faciale; réduisez-la si le modèle ne trouve pas de visage dans votre image. Un réglage plus grand offre une détection plus précise, mais s’exécute plus lentement et risque davantage de ne pas détecter un visage. |
| `base_1_5_model_repo` |  | string | no | `SG161222/Realistic_Vision_V4.0_noVAE` |  | URL du modèle Base 1.5; par défaut, `SG161222/Realistic_Vision_V4.0_noVAE`. |
| `base_sdxl_model_repo` |  | string | no | `SG161222/RealVisXL_V3.0` |  | URL du modèle Base SDXL; par défaut, `SG161222/RealVisXL_V3.0`. |
| `enable_safety_checker` |  | boolean | no | `true` |  | La vérification peut être assouplie en définissant false, si l’appelant est autorisé. |

File parameters (`face_image_url`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/ip-adapter-face-id?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/ip-adapter-face-id?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ip-adapter-face-id", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "ip-adapter-face-id",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "ip-adapter-face-id",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 60,
    "usd": "0.06",
    "charged": 60,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "image": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768
    },
    "seed": 42
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `image` | object {url, content_type, file_name, file_size, width, height} | Informations sur le fichier de l’image générée. |
| `seed` | integer | Graine de génération d’image, incluant la valeur choisie aléatoirement si l’entrée n’a pas fourni de graine; sinon, elle répète la valeur fournie. |

## Related models

- [FLUX.1 Kontext \[pro\]](https://doitong.com/developers/models/flux-pro/kontext.md) (`flux-pro/kontext`): $0.04 / image
- [GPT Image 2.5 Edit](https://doitong.com/developers/models/openai/gpt-image-2.5/flare/edit.md) (`openai/gpt-image-2.5/flare/edit`): from $0.12 / image
- [Nano Banana 2 Edit](https://doitong.com/developers/models/nano-banana-2/edit.md) (`nano-banana-2/edit`): from $0.06 / image
- [Nano Banana Pro Edit](https://doitong.com/developers/models/nano-banana-pro/edit.md) (`nano-banana-pro/edit`): from $0.15 / image
- [Qwen Image 3 Edit](https://doitong.com/developers/models/alibaba/qwen-image-3/edit.md) (`alibaba/qwen-image-3/edit`): from $0.04 / image
- [Seedream 5.0 Pro Edit](https://doitong.com/developers/models/bytedance/seedream/v5/pro/edit.md) (`bytedance/seedream/v5/pro/edit`): from $0.0675 / run of output image
- [Hunyuan Image · v3 · Instruct · Edit](https://doitong.com/developers/models/hunyuan-image/v3/instruct/edit.md) (`hunyuan-image/v3/instruct/edit`): $0.174 / image
- [Hunyuan World](https://doitong.com/developers/models/hunyuan_world.md) (`hunyuan_world`): $0.15 / image

## Links

- HTML page: https://doitong.com/developers/models/ip-adapter-face-id
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=ip-adapter-face-id
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ip-adapter-face-id