# Topaz Gigapixel Standard 2

Topaz Gigapixel Standard 2 transforms images into clean, enlarged outputs with balanced sharpness, noise reduction, and natural detail for photos and graphics.

## API Information

- **Model Slug:** topaz-gigapixel-standard-2
- **Branded URL:** https://www.eachlabs.ai/topaz/topaz/topaz-gigapixel-standard-2
- **Provider:** Topaz
- **Category:** Image to Image
- **Output Type:** image
- **Status:** active
- **Base Cost:** $0.10–$4.30 per image, depending on output size
- **Estimated Processing Time:** 10 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/topaz-gigapixel-standard-2

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.10–$4.30 per image, depending on output size
- **Pricing Details:** up to 24 MP: $0.1
- **Pricing Details:** up to 48 MP: $0.2
- **Pricing Details:** up to 72 MP: $0.3
- **Pricing Details:** up to 96 MP: $0.4
- **Pricing Details:** up to 120 MP: $0.5
- **Pricing Details:** up to 144 MP: $0.6
- **Pricing Details:** up to 168 MP: $0.7
- **Pricing Details:** up to 192 MP: $0.8
- **Pricing Details:** + each further 24 MP above 192 MP: $0.1
- **Pricing Details:** largest output (1024 MP): $4.30

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| image_url | string | Yes | - | - | URL of the source image to upscale. Supported formats: JPEG, PNG. The input image must not exceed 512 megapixels. |
| output_width | integer | No | - | 1–32000 | Desired output width in pixels. If only width or height is set, Topaz scales the other dimension proportionally. |
| output_height | integer | No | - | 1–32000 | Desired output height in pixels. If only width or height is set, Topaz scales the other dimension proportionally. |
| output_format | string | No | jpeg | jpeg, jpg, png, tiff, tif | Output image format. Default: jpeg. |
| crop_to_fill | boolean | No | false | - | Crop the image to fill the requested dimensions instead of letterboxing. Default: false. |
| subject_detection | string | No | - | foreground, background, all | Where Standard 2 enhancements are applied. Omit to let Topaz choose automatically. |
| strength | number | No | - | 0.01–1 | Model strength. Higher values may look less realistic. Range: 0.01-1. |
| sharpen | number | No | - | 0–1 | Slightly sharpens the image. Range: 0-1. |
| denoise | number | No | - | 0–1 | Reduces image noise. Range: 0-1. |
| fix_compression | number | No | - | 0–1 | Reduces compression artifacts. Range: 0-1. |
| face_enhancement | boolean | No | false | - | Enable Topaz face recovery for detected faces. Strength and creativity are required when enabled. |
| face_enhancement_strength | number | No | - | 0–1 | Face recovery strength. Required when face enhancement is enabled. Range: 0-1. |
| face_enhancement_creativity | number | No | - | 0–1 | Face recovery creativity. Required when face enhancement is enabled. Range: 0-1. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "topaz-gigapixel-standard-2",
  "input": {
    "image_url": "https://cdn-us.eachlabs.ai/defaults/723f9b735a36469f9de4799d042ca7f6.png"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated image)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.