# Tencent Image Upscaler — Atlas Cloud API

> Tencent Image Upscaler (MPS advanced super-resolution)

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

- **Model ID**: `tencent/image/upscaler`
- **Modality**: Image
- **Model page**: https://www.atlascloud.ai/models/tencent/image/upscaler
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.024 per image
- 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_image` with `model: "tencent/image/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 image tencent/image/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/generateImage` — 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/image/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/image/upscaler"`

- **`image_url`** (`string`, _required_):
  URL of the source image to enhance. Must be a publicly accessible HTTP(S) URL (user-uploaded or third-party-model output are both supported). Supported formats: .jpg/.jpeg/.png.

- **`type`** (`string`, _optional_):
  Advanced super-resolution type. standard = generic upscale (fastest ~5s); super = AIGC scenes (~15s); ultra = more detail enhancement (~15s); fidelity = ultra high fidelity for e-commerce (~30s).
  - Default: `"ultra"`
  - Options: "standard", "super", "ultra", "fidelity"

- **`mode`** (`string`, _optional_):
  Super-resolution mode. percent = scale by a factor (use percent); aspect = keep aspect ratio, scale to fit given dimensions; fixed = force exact dimensions.
  - Default: `"percent"`
  - Options: "percent", "aspect", "fixed"

- **`percent`** (`number`, _optional_):
  Scale factor for mode=percent. 1.0 = keep resolution (enhance only), 2.0 = 2x. Range 1.0~10.0.
  - Default: `2`
  - Min: 1
  - Max: 10

- **`width`** (`integer`, _optional_):
  Target width in pixels (for mode=aspect / fixed).
  - Min: 1

- **`height`** (`integer`, _optional_):
  Target height in pixels (for mode=aspect / fixed).
  - Min: 1

- **`long_side`** (`integer`, _optional_):
  Target long-edge in pixels (for mode=aspect / fixed). Alternative to width/height.
  - Min: 1

- **`short_side`** (`integer`, _optional_):
  Target short-edge in pixels (for mode=aspect / fixed). Alternative to width/height.
  - Min: 1

- **`encode_format`** (`string`, _optional_):
  Output image encode format.
  - Default: `"JPEG"`
  - Options: "JPEG", "PNG", "WEBP", "BMP"

- **`encode_quality`** (`integer`, _optional_):
  Output image encode quality (1-100). Applies to lossy formats.
  - Default: `80`
  - Min: 1
  - Max: 100



**Required Parameters Example**:

```json
{
  "model": "tencent/image/upscaler",
  "image_url": ""
}
```


**Full Example**:

```json
{
  "model": "tencent/image/upscaler",
  "image_url": "",
  "type": "ultra",
  "mode": "percent",
  "percent": 2,
  "width": 1,
  "height": 1,
  "long_side": 1,
  "short_side": 1,
  "encode_format": "JPEG",
  "encode_quality": 80
}
```


### 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 image(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/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "tencent/image/upscaler",
  "image_url": "",
  "type": "ultra",
  "mode": "percent",
  "percent": 2,
  "width": 1,
  "height": 1,
  "long_side": 1,
  "short_side": 1,
  "encode_format": "JPEG",
  "encode_quality": 80
}'

# 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/image/upscaler)

## About this model

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

### Tencent Image Upscaler

Tencent Image Upscaler enhances an existing image to a higher resolution and better quality using Tencent Cloud MPS (Media Processing Service) advanced super-resolution. Provide a public image URL, pick a super-resolution type and scaling mode, and receive an enhanced image URL.

#### Highlights

- **Image-to-image enhancement:** Upscale and enhance an existing image without changing its content. User-uploaded images and third-party-model outputs are both supported.
- **Four SR engines:** `standard` (generic, fastest), `super` (AIGC scenes), `ultra` (more detail enhancement, default), and `fidelity` (ultra high fidelity for e-commerce).
- **Flexible scaling:** Scale by a factor (`percent`), fit given dimensions keeping aspect ratio (`aspect`), or force exact dimensions (`fixed`).
- **Hosted output:** Enhanced images 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/image/upscaler`. |
| `image_url` | Yes | Input image URL. Must be a publicly accessible HTTP(S) URL — Tencent MPS fetches it before processing, so signed URLs should be long-lived. Supported formats: `.jpg` / `.jpeg` / `.png`. |
| `type` | No | Super-resolution engine: `standard` (fastest ~5s), `super` (AIGC scenes ~15s), `ultra` (more detail, default ~15s), `fidelity` (ultra high fidelity ~30s). |
| `mode` | No | Scaling mode: `percent` (default, scale by a factor), `aspect` (keep aspect ratio, scale to fit given dimensions), `fixed` (force exact dimensions). |
| `percent` | No | Scale factor for `mode=percent`. `1.0` = keep resolution (enhance only), `2.0` = 2x. Range `1.0`–`10.0`. Default `2.0`. |
| `width` | No | Target width in pixels (for `mode=aspect` / `fixed`). |
| `height` | No | Target height in pixels (for `mode=aspect` / `fixed`). |
| `long_side` | No | Target long-edge in

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

---

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