# Creative Upscaler API

> Mise à l'échelle créative fondée sur la diffusion, ajoutant des détails, avec base SD 1.5 ou SDXL et contrôle de la forme

Agrandit une image depuis `image_url` selon un facteur `scale` de 1 à 5 tout en générant de nouveaux détails. `model_type` vaut SD_1_5 ou SDXL, `creativity` et `detail` définissent l’ampleur des modifications, et `shape_preservation` conserve la structure d’origine. Sans `prompt`, un prompt est généré automatiquement. Les URL de modèles de base personnalisés, de LoRA et d’embeddings sont prises en charge.

- Model id: `creative-upscaler`
- Made by: Open model
- Category: Upscale
- Output: image
- Charged by usage (up to $1.125 per run, typical $0.007; the rest of the hold is refunded): $0.00125 / second of processing time (cheapest run $0.007 (7 API credits))
- Run: `POST https://api.doitong.ru/v1/run/creative-upscaler`
- Quote: `POST https://api.doitong.ru/v1/quote/creative-upscaler`
- Docs page: https://doitong.com/fr/developers/models/creative-upscaler

## Pricing

Price: **$0.00125 / second of processing time**. Charged by actual usage at $0.00125 / second of processing time: up to $1.125 per run (the quote gives the maximum for your input), the rest is refunded automatically after the run. A typical run costs $0.007.

The full example input below holds up to $1.125 = 1125 API credits (up to 900 s of processing time × $0.00125) when it starts; a typical run costs $0.007 (7 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). This model is charged by usage: `POST https://api.doitong.ru/v1/quote/creative-upscaler` with the same JSON body returns the most the run can cost for that input (`credits`, debited when the run starts); after the run you pay the usage the model reports and the rest is refunded automatically. An input whose maximum would exceed the per-run limit is refused with 422. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `model_type` |  | enum (string) | no | `SD_1_5` | `SD_1_5`, `SDXL` | Type de modèle utilisé pour l’agrandissement ; par défaut, SD_1_5. |
| `image_url` | `image` | string (image URL) | yes |  |  | Image source à agrandir. |
| `prompt` |  | string \| null | no |  |  | Prompt de génération d’image, créé par BLIP2 lorsque vous l’omettez. Si vous fournissez le vôtre, incluez autant de détails descriptifs que possible pour obtenir les meilleurs résultats. |
| `scale` |  | number | no | `2` | 1 – 5 | Augmentez ce facteur d’échelle pour agrandir l’image de sortie. |
| `creativity` |  | number | no | `0.5` | 0 – 1 | Degré d’écart autorisé par rapport à l’original. |
| `detail` |  | number | no | `1` | 0 – 5 | Quantité de détails ajoutés. |
| `shape_preservation` |  | number | no | `0.25` | 0 – 3 | Degré de conservation de la forme de l’image source. |
| `prompt_suffix` |  | string | no | `high quality, highly detailed, high resolution, sharp` |  | Fin de prompt commune permettant d’ajouter à tous les prompts des jetons d’incorporation ou des formulations telles que 'high quality'. |
| `negative_prompt` |  | string | no | `blurry, low resolution, bad, ugly, low quality, pixelated, interpolated, compression artifacts, noisey, grainy` |  | Prompt négatif indiquant les détails d’image indésirables. Il 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 permettant de reproduire des images dans Stable Diffusion. Une image peut être reproduite exactement à chaque exécution en conservant la version du modèle, le prompt et la graine inchangés. |
| `guidance_scale` |  | number | no | `7.5` | 0 – 16 | Force d'adhérence au prompt pour la sélection d'image, exprimée comme CFG (Classifier Free Guidance). |
| `num_inference_steps` |  | integer | no | `20` | 1 – 200 | Nombre d’étapes d’inférence pour la génération d’image, avec une meilleure qualité aux valeurs élevées au prix d’un temps de génération plus long. |
| `enable_safety_checks` |  | boolean | no | `true` |  | Option de vérification de sécurité qui, lorsqu’elle vaut true, remplace par une image noire tout résultat détecté comme contenant du contenu potentiellement dangereux. |
| `skip_ccsr` |  | boolean | no | `false` |  | Contournement du prétraitement CCSR lorsqu’il est activé ; l’image est envoyée directement au modèle de créativité. |
| `override_size_limits` |  | boolean | no | `false` |  | Autorisation des fichiers volumineux dont le traitement peut être très long. |
| `base_model_url` |  | string \| null | no |  |  | URL du modèle de base pour l’agrandissement. |
| `additional_lora_url` |  | string | no |  |  | Indiquez un LORA supplémentaire pour l’agrandissement en fournissant l’URL de son modèle. Sans valeur, la valeur par défaut est None. |
| `additional_lora_scale` |  | number | no | `1` |  | Ajustez l’intensité avec laquelle le LORA supplémentaire affecte l’agrandissement via son paramètre d’échelle, dont la valeur par défaut est 1.0. |
| `additional_embedding_url` |  | string | no |  |  | Fournissez des incorporations supplémentaires pour l’agrandissement en les indiquant avec une URL. Sans valeur, la valeur par défaut est None. |

File parameters (`image`) 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
{
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

A fuller example:

```json
{
  "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

## 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.ru/v1/run/creative-upscaler?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }'

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

### JavaScript

```javascript
const API = "https://api.doitong.ru/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/creative-upscaler?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }),
});
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.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/creative-upscaler", 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.ru/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": "creative-upscaler",
      "input": {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
      },
      "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": "creative-upscaler",
  "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": 1125,
    "usd": "1.125",
    "charged": 1125,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `image` | object {url, content_type, file_name, file_size, width, height} | Informations de fichier pour l’image générée. |
| `seed` | integer | Seed de génération d'images, y compris la valeur choisie aléatoirement si l'entrée n'en fournissait pas ; sinon, il reprend la valeur fournie. |

## Related models

- [Topaz Image Upscale](https://doitong.com/developers/models/topaz/upscale/image/precision.md) (`topaz/upscale/image/precision`): $0.08 / 24 megapixels of output image
- [Topaz Video Upscale](https://doitong.com/developers/models/topaz/upscale/video/precision.md) (`topaz/upscale/video/precision`): from $0.00667 / second of input video
- [AuraSR](https://doitong.com/developers/models/aura-sr.md) (`aura-sr`): $0.001111 / second of processing time
- [DRCT-Super-Resolution](https://doitong.com/developers/models/drct-super-resolution.md) (`drct-super-resolution`): $0.0045 / megapixel of output image
- [Flashvsr](https://doitong.com/developers/models/flashvsr/upscale/video.md) (`flashvsr/upscale/video`): $0.0005 / megapixel of output video
- [Fooocus Upscale or Vary](https://doitong.com/developers/models/fooocus/upscale-or-vary.md) (`fooocus/upscale-or-vary`): $0.007 / image
- [Upscale Images](https://doitong.com/developers/models/esrgan.md) (`esrgan`): $0.000575 / second of processing time
- [Video Upscaler](https://doitong.com/developers/models/video-upscaler.md) (`video-upscaler`): $0.0008 / megapixel of output video

## Links

- HTML page: https://doitong.com/developers/models/creative-upscaler
- 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=creative-upscaler
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/creative-upscaler