# Tencent Video Upscaler — Atlas Cloud API

> Tencent Video Upscaler (MPS super-resolution / enhancement)

This is the machine-readable API reference for **Tencent Video Upscaler** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `tencent/video/upscaler`
- **Built by**: TENCENT
- **Modality**: Video
- **Model page**: https://www.atlascloud.ai/models/tencent/video/upscaler
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.004 per second of generated video
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_video` with `model: "tencent/video/upscaler"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate video tencent/video/upscaler -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateVideo` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `tencent/video/upscaler`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  model name
  - Default: `"tencent/video/upscaler"`

- **`video_url`** (`string`, _required_):
  URL of the source video to enhance. Must be a publicly accessible HTTP(S) URL (user-uploaded or third-party-model output are both supported). Signed URLs should be long-lived — Tencent MPS fetches the video before processing.

- **`template`** (`string`, _optional_):
  Enhancement template. The frontend shows the label; the backend maps the slug to the corresponding MPS template ID (Definition).
  - Default: `"anime-enhance-4k"`
  - Options: "live-action-enhance-720p", "live-action-enhance-1080p", "live-action-enhance-2k", "live-action-enhance-4k", "anime-enhance-720p", "anime-enhance-1080p", "anime-enhance-2k", "anime-enhance-4k", "restore-720p", "restore-1080p", "restore-2k", "restore-4k", "live-action-smallface-720p", "live-action-smallface-1080p", "live-action-smallface-2k", "live-action-smallface-4k", "anime-smallface-720p", "anime-smallface-1080p", "anime-smallface-2k", "anime-smallface-4k", "seedance2-enhance-720p", "seedance2-enhance-1080p", "seedance2-enhance-2k", "seedance2-enhance-4k"

- **`short`** (`integer`, _optional_):
  Output short-edge in pixels. Range is constrained by the chosen template tier (see x-depends-on). Special value 0 = keep source resolution.
  - Default: `0`
  - Min: 0
  - Max: 2160

- **`fps`** (`integer`, _optional_):
  Smart frame-interpolation target FPS. Omit to keep source frame rate.
  - Min: 1

- **`keep_metadata`** (`boolean`, _optional_):
  Whether to preserve the source media metadata.
  - Default: `true`



**Required Parameters Example**:

```json
{
  "model": "tencent/video/upscaler",
  "video_url": ""
}
```


**Full Example**:

```json
{
  "model": "tencent/video/upscaler",
  "video_url": "",
  "template": "anime-enhance-4k",
  "short": 0,
  "fps": 1,
  "keep_metadata": true
}
```


### Output Schema

The API returns the following output format:


- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created.

- **`has_nsfw_contents`** (`array[boolean]`, _optional_):
  Array of boolean values indicating NSFW detection for each output.

- **`id`** (`string`, _optional_):
  Unique identifier for the prediction.

- **`model`** (`string`, _optional_):
  Model ID used for the prediction.

- **`outputs`** (`array[string]`, _optional_):
  Array of URLs to the enhanced video(s).

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.



**Example Response**:

```json
{
  "created_at": "",
  "has_nsfw_contents": [],
  "id": "",
  "model": "",
  "outputs": [
    ""
  ],
  "status": "",
  "urls": {}
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "tencent/video/upscaler",
  "video_url": "",
  "template": "anime-enhance-4k",
  "short": 0,
  "fps": 1,
  "keep_metadata": true
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/tencent/video/upscaler)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### Tencent Video Upscaler

Tencent Video Upscaler enhances an existing video to a higher output resolution and better quality using Tencent Cloud MPS (Media Processing Service) large-model super-resolution. Provide a public video URL, pick an enhancement template, and receive a playable enhanced video URL.

#### Highlights

- **Video-to-video enhancement:** Improve an existing clip (up to 4K) without changing the source content. User-uploaded videos and third-party-model outputs are both supported.
- **Scene-tuned templates:** Choose a template matched to your content and target resolution — live-action / anime-comic AI enhance, old-film & low-quality restoration (denoise + face enhance + descratch), distant small-face optimization, or Seedance2-tuned enhancement — at 720P / 1080P / 2K / 4K.
- **Optional fine control:** Override the output short-edge and interpolate the frame rate when needed; otherwise the template's tier and the source frame rate are used.
- **Hosted output:** Enhanced videos are transferred to AtlasCloud storage and returned as long-lived URLs (the upstream Tencent COS URL is never exposed).

#### Parameters

| Parameter | Required | Description |
|-----------|----------|-------------|
| `model` | Yes | Use `tencent/video/upscaler`. |
| `video_url` | Yes | Input video URL. Must be a publicly accessible HTTP(S) URL — Tencent MPS fetches it before processing, so signed URLs should be long-lived. |
| `template` | Yes | Enhancement template. Selects the scene and target resolution tier (see the table below). Default `anime-enhance-4k`. |
| `short` | No | Output short-edge in pixels, constrained by the chosen template tier: 720P `(0,720]`, 1080P `(720,1080]`, 2K `(1080,1440]`, 4K `(1440,2160]`. Omit to use the template's default output size. Does not affect billing. |
| `fps` | No | Target frame rate (frame interpolation). Omit to keep the source frame rate. |
| `keep_metadata` | No | Whether to preserve the source media metadata. Default `true`. |

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/tencent/video/upscaler · Docs: https://www.atlascloud.ai/docs