# Scail 2 API

> Anima uma imagem de personagem de referência com movimento de um vídeo condutor ou insere-a na cena original

Recebe um `image_url` de personagem de referência e um `video_url` condutor que mostra uma pessoa, várias pessoas ou um animal. No modo `animation`, a personagem executa o movimento condutor; no modo `replacement`, substitui o sujeito mantendo a cena. A resolução é 512p ou 704p, com a orientação escolhida a partir da imagem. `driving_type` pode usar condução direta de ponta a ponta ou um esqueleto de pose explícito.

- Model id: `scail-2`
- Made by: Open model
- Category: Video to Video
- Output: video
- Price per second of your input video: $0.20 / second of input video (cheapest run $0.20 (200 API credits))
- Run: `POST https://api.doitong.com/v1/run/scail-2`
- Quote: `POST https://api.doitong.com/v1/quote/scail-2`
- Docs page: https://doitong.com/pt-PT/developers/models/scail-2

## Pricing

Price: **$0.20 / second of input video**. Price per second of your input video: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $2.00 = 2000 API credits (10 s input video × $0.20).

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/scail-2` 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

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 |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | Prompt que especifica o vídeo de saída pretendido. |
| `image_url` | `image` | string (image URL) | yes |  |  | URL da imagem de referência da personagem que fornece a personagem a animar ou substituir por um sujeito, sendo o vídeo de condução responsável por determinar a animação ou substituição. |
| `video_url` | `video` | string (video URL) | yes |  |  | Forneça por URL um vídeo de condução de movimento, com uma única pessoa, várias pessoas ou um animal. |
| `mode` |  | enum (string) | no | `animation` | `animation`, `replacement` | Escolha como utilizar a personagem de referência: `replacement` preserva a cena original, mas substitui a personagem pelo sujeito de condução; `animation` aplica o movimento de condução à personagem. |
| `driving_type` |  | enum (string) | no | `end_to_end` | `end_to_end`, `pose` | O movimento da animação provém diretamente de um vídeo de condução mascarado pelo SAM3 com `end_to_end`, a opção predefinida e recomendada para máxima robustez. Em alternativa, `pose` utiliza NLF/DWPose para gerar um esqueleto explícito a partir desse vídeo, oferecendo maior controlo com entradas difíceis. |
| `subject_type` |  | enum (string) | no | `human` | `human`, `animal` | Seleção do sujeito do vídeo de condução, com `animal` a configurar o prompt de deteção do SAM3 para sujeitos não-`human`. |
| `resolution` |  | enum (string) | no | `512p` | `512p`, `704p` | Resolução da saída com orientação determinada automaticamente pela proporção da imagem de referência. Em paisagem, 512p corresponde a 896x512 e 704p a 1280x704; em retrato, utiliza 512x896 e 704x1280, respetivamente. |
| `num_inference_steps` |  | integer | no | `40` | 2 – 50 | Número de passos de amostragem da difusão. Aumentá-lo melhora a qualidade, mas demora mais tempo. |
| `guidance_scale` |  | number | no | `5` | 1 – 10 | Intensidade da orientação sem classificador, equilibrando a adesão ao prompt e a criatividade. |
| `shift` |  | number | no | `3` | 1 – 10 | Deslocamento do esquema de ruído para correspondência de fluxo, com uma definição recomendada de 3.0 ao utilizar 512p. |
| `seed` |  | integer \| null | no |  |  | Semente da geração incluída na resposta, quer tenha sido fornecida explicitamente, quer selecionada aleatoriamente porque a entrada foi deixada vazia. |
| `enable_safety_checker` |  | boolean | no | `true` |  | A filtragem pode ser flexibilizada definindo false, desde que o autor do pedido esteja autorizado. |

File parameters (`image`, `video`) 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",
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

## 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/scail-2?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",
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# 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/scail-2?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",
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }),
});
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",
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/scail-2", 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": "scail-2",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
        "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
      },
      "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": "scail-2",
  "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": 2000,
    "usd": "2.00",
    "charged": 2000,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "seed": 42,
    "preprocessing_video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "preprocessing_mask_video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "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 |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Ficheiro de vídeo produzido pela geração. |
| `seed` | integer | Semente utilizada para geração de vídeo. |
| `preprocessing_video` | object {url, content_type, file_name, file_size} \| null | Vídeo de depuração que contém a entrada de condicionamento da pose Stage-A fornecida ao modelo de difusão, disponível apenas com `output_preprocessing=true`. O conteúdo depende de `driving_type`: `end_to_end` utiliza imagens de condução mascaradas pelo SAM3, enquanto `driving_type=pose` utiliza um esqueleto gerado pelo NLF/DWPose. |
| `preprocessing_mask_video` | object {url, content_type, file_name, file_size} \| null | Vídeo da máscara de condução Stage-A para depuração, disponível apenas com `output_preprocessing=true`. |

## Related models

- [AMT Interpolation](https://doitong.com/developers/models/amt-interpolation.md) (`amt-interpolation`): $0.000575 / second of processing time
- [AnimateDiff Turbo · Video to Video](https://doitong.com/developers/models/fast-animatediff/turbo/video-to-video.md) (`fast-animatediff/turbo/video-to-video`): $0.00125 / second of processing time
- [AnimateDiff · Video to Video](https://doitong.com/developers/models/fast-animatediff/video-to-video.md) (`fast-animatediff/video-to-video`): $0.00125 / second of processing time
- [Bernini-R Edit Video](https://doitong.com/developers/models/bernini-r/edit-video.md) (`bernini-r/edit-video`): from $0.04 / second of output video
- [Bernini-R Reference Edit Video](https://doitong.com/developers/models/bernini-r/reference-edit-video.md) (`bernini-r/reference-edit-video`): from $0.04 / second of output video
- [DWPose Pose Prediction · Video](https://doitong.com/developers/models/dwpose/video.md) (`dwpose/video`): $0.0006 / second of processing time
- [Editto](https://doitong.com/developers/models/editto.md) (`editto`): from $0.04 / second of output video
- [ID-V2V](https://doitong.com/developers/models/id-v2v.md) (`id-v2v`): $0.20 / second of output video

## Links

- HTML page: https://doitong.com/developers/models/scail-2
- 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=scail-2
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/scail-2