# Topaz Upscale Video Generative API

> Bộ nâng cấp video tạo sinh với các mô hình Starlight có thể chọn, hướng đến cảnh quay bị nén hoặc lưu trữ

Tăng cường và nâng cấp video bằng các mô hình Starlight dựa trên diffusion, được chọn qua `model`: Precise 2.6, HQ, Mini, Sharp hoặc Fast 2. `upscale_factor` nằm trong khoảng từ 1 đến 4, còn `target_fps` (16-60) bật nội suy khung hình khi khác nguồn. `softness` (1-5) chỉ áp dụng cho Starlight Precise 2.6. Codec đầu ra là H265 hoặc H264 khi yêu cầu.

- Model id: `topaz/upscale/video/generative`
- Made by: Topaz Labs
- Category: Upscale
- Output: video
- Price per second of your input video: from $0.06 / second of input video (cheapest run $0.10 (100 API credits))
- Run: `POST https://api.doitong.ru/v1/run/topaz/upscale/video/generative`
- Quote: `POST https://api.doitong.ru/v1/quote/topaz/upscale/video/generative`
- Docs page: https://doitong.com/vi/developers/models/topaz/upscale/video/generative

## Pricing

Price: **from $0.06 / second of input video** (the lowest tier; the quote prices your exact input). 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.

Price by tier:

- Starlight Fast 2, up to 1080p: $0.06 / second of input video
- up to 1080p: $0.12 / second of input video
- Starlight Fast 2, up to 1080p, frame rate: $0.12 / second of input video
- Starlight Fast 2, 4K: $0.13 / second of input video
- Starlight Fast 2, above 4K: $0.2311 / second of input video
- up to 1080p, frame rate: $0.24 / second of input video
- 4K: $0.255 / second of input video
- Starlight Fast 2, 4K, frame rate: $0.26 / second of input video
- above 4K: $0.4533 / second of input video
- Starlight Fast 2, above 4K, frame rate: $0.4622 / second of input video
- 4K, frame rate: $0.51 / second of input video
- above 4K, frame rate: $0.9067 / second of input video

The full example input below costs $2.60 = 2600 API credits (10 s input video × $0.255 (4K), rounded up to the next $0.10).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.ru/v1/quote/topaz/upscale/video/generative` 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 |
|---|---|---|---|---|---|---|
| `video_url` | `video` | string (video URL) | yes |  |  | URL video nguồn để nâng độ phân giải. |
| `model` |  | enum (string) | no | `Starlight Precise 2.6` | `Starlight Precise 2.6`, `Starlight HQ`, `Starlight Mini`, `Starlight Sharp`, `Starlight Fast 2` | Lựa chọn mô hình khuếch tán tạo sinh để nâng cao video. Để phục hồi lưu trữ, dùng Starlight Mini; để phục hồi nhanh với chi tiết sắc nét, dùng Starlight Sharp; để đạt chất lượng tối đa từ cảnh quay độ phân giải cao, dùng Starlight HQ; và để có video do AI tạo chân thực hơn, dùng Starlight Precise 2.6. Trong các mô hình nâng độ phân giải khuếch tán, Starlight Fast 2 vừa nhanh nhất vừa rẻ nhất. |
| `upscale_factor` |  | number | no | `2` | 1 – 4 | Hệ số tỷ lệ video; giá trị 2.0 tăng gấp đôi cả hai kích thước khung hình. |
| `target_fps` |  | integer \| null | no |  | 16 – 60 | Tốc độ khung hình đầu ra mục tiêu; khớp với FPS nguồn sẽ tắt nội suy, chỉ FPS khác mới bật nội suy. |
| `softness` |  | number \| null | no |  | 1 – 5 | Thiết lập độ mềm chỉ có trong Starlight Precise 2.6, sử dụng giá trị mặc định khi bỏ qua. Chọn 1 để có đầu ra sắc nét nhất hoặc 5 để có đầu ra mềm nhất. |
| `H264_output` |  | boolean | no | `false` |  | Kiểm soát việc video đầu ra sử dụng mã hóa H264 thay vì H265 mặc định. |

File parameters (`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
{
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

A fuller example:

```json
{
  "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.ru/v1/run/topaz/upscale/video/generative?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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.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/topaz/upscale/video/generative?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "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/topaz/upscale/video/generative", 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": "topaz/upscale/video/generative",
      "input": {
        "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": "topaz/upscale/video/generative",
  "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": 2600,
    "usd": "2.60",
    "charged": 2600,
    "refunded": 0
  },
  "input": {
    "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
    }
  },
  "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Tệp video được tạo bằng cách nâng độ phân giải. |

## Related models

- [Topaz Upscale Video Creative](https://doitong.com/developers/models/topaz/upscale/video/creative.md) (`topaz/upscale/video/creative`): from $0.30 / second of input video
- [Topaz Video Upscale](https://doitong.com/developers/models/topaz/upscale/video/precision.md) (`topaz/upscale/video/precision`): from $0.00667 / second of input video
- [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 Upscale Image Creative](https://doitong.com/developers/models/topaz/upscale/image/creative.md) (`topaz/upscale/image/creative`): $0.08 / 2 megapixels of output image
- [Topaz Upscale Image Generative](https://doitong.com/developers/models/topaz/upscale/image/generative.md) (`topaz/upscale/image/generative`): from $0.01 / megapixel of output image
- [Topaz Upscale Image Transparent](https://doitong.com/developers/models/topaz/upscale/image/transparent.md) (`topaz/upscale/image/transparent`): $0.08 / 24 megapixels of output image
- [AuraSR](https://doitong.com/developers/models/aura-sr.md) (`aura-sr`): $0.001111 / second of processing time
- [Bria Increase Resolution](https://doitong.com/developers/models/bria/increase-resolution.md) (`bria/increase-resolution`): $0.04 / image

## Links

- HTML page: https://doitong.com/developers/models/topaz/upscale/video/generative
- 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=topaz/upscale/video/generative
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/topaz/upscale/video/generative