# Topaz Image Upscale

> Professional-grade image upscaler from Topaz Labs offering five specialized models (Standard, Low Resolution, CGI, High Fidelity, Text Refine) with optional face enhancement

## Quick Reference

- Model ID: topaz-image-upscale
- Creator: Topaz Labs
- Status: active
- Base URL: https://api.lumenfall.ai/openai/v1

## Specifications

- Max Input Images: 1
- Input Modalities: image
- Output Modalities: image
- Supported Modes: Upscale

## API Parameters

The compiled parameter schema for this model is available via the API: `GET /v1/models/topaz-image-upscale?schema=true`.

### Media Inputs

- `image` (file) — REQUIRED: Input image to upscale
- `scale_factor` (number) — REQUIRED: Factor by which to upscale the image. Values: 2x, 4x, 6x, None

### Output & Format

- `response_format` (string): How to return the image. Default: url. Values: url, b64_json
- `output_format` (string): Output image format. Values: png, jpeg, gif, webp, avif
- `output_compression` (integer): Compression level for lossy formats (JPEG, WebP, AVIF)
- `n` (integer): Number of images to generate. Default: 1

### Additional Parameters

- `crop_to_fill` (boolean): Crop to fill output dimensions. Only available via fal
- `enhance_model` (string): Enhancement model to use. Values: CGI, High Fidelity V2, Low Resolution V2, Standard V2, Text Refine. Only available via replicate
- `face_enhancement` (boolean): Enable face enhancement
- `face_enhancement_creativity` (number): Creativity for face enhancement (0-1). Only available via replicate
- `face_enhancement_strength` (number): Strength of face enhancement (0-1)
- `model` (string): Enhancement model to use. Values: CGI, High Fidelity V2, Low Resolution V2, Standard V2, Text Refine. Only available via fal
- `subject_detection` (string): Subject detection mode. Values: All, Background, Foreground, None


## Model Identifiers

- Primary Slug: topaz-image-upscale
- Aliases: topaz-image, gigapixel

## Dates

- Released: April 2025

## Tags

image-upscaling, super-resolution, image-enhancement, high-quality

## Available Providers

### Replicate

- Config Key: replicate/topaz-image-upscale
- Provider Model ID: topazlabs/image-upscale
- Pricing: 
  - Note: Tiered pricing based on output image megapixels.
  - Note: Up to 24 MP: $0.05, up to 48 MP: $0.10, up to 60 MP: $0.15, up to 96 MP: $0.20, up to 132 MP: $0.24, up to 168 MP: $0.29, up to 336 MP: $0.53, up to 512 MP: $0.82
  - Source: https://replicate.com/topazlabs/image-upscale

### fal.ai

- Config Key: fal/topaz-image-upscale
- Provider Model ID: fal-ai/topaz/upscale/image
- Pricing: 
  - Note: Tiered pricing based on output image megapixels.
  - Note: Up to 24 MP: $0.08, up to 48 MP: $0.16, up to 96 MP: $0.32, up to 512 MP: $1.36
  - Source: https://fal.ai/models/fal-ai/topaz/upscale/image


## Arena Benchmarks

### Weave Warfare

- Elo: 1134
- Record: 6W / 8L / 0T (14 battles)
- Rank: #2 of 4


## Image Gallery

1 images available for this model. Browse all at https://lumenfall.ai/models/topaz-labs/topaz-image-upscale/gallery

### Arena Competition Results

- [Weave Warfare](https://assets.lumenfall.ai/NojgeYSCz42YiO6Cy17lt216CCap8A9z1DDelFA9MVY/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/psm3p6hiagm7nvzxxaxcs1ehafs6@jpeg): #2 of 4 (Elo 1134)

## Code Examples

### Upscale (/v1/images/edits)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/edits \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -F "model=topaz-image-upscale" \
  -F "image=@source.png" \
  -F "prompt=Add a starry night sky to this image" \
  -F "size=1024x1024"

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.edit({
  model: 'topaz-image-upscale',
  image: fs.createReadStream('source.png'),
  prompt: 'Add a starry night sky to this image',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.edit(
    model="topaz-image-upscale",
    image=open("source.png", "rb"),
    prompt="Add a starry night sky to this image",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)


## Frequently Asked Questions

### How do I use Topaz Image Upscale via API?

You can use Topaz Image Upscale through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "topaz-image-upscale". Code examples are available in Python, JavaScript, and cURL.

### Which providers offer Topaz Image Upscale?

Topaz Image Upscale is available through Replicate and fal.ai on Lumenfall. Lumenfall automatically routes requests to the best available provider.

## Links

- Model Page: https://lumenfall.ai/models/topaz-labs/topaz-image-upscale
- About: https://lumenfall.ai/models/topaz-labs/topaz-image-upscale/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/topaz-labs/topaz-image-upscale/providers
- API Reference: https://lumenfall.ai/models/topaz-labs/topaz-image-upscale/api
- Benchmarks: https://lumenfall.ai/models/topaz-labs/topaz-image-upscale/benchmarks
- Use Cases: https://lumenfall.ai/models/topaz-labs/topaz-image-upscale/use-cases
- Gallery: https://lumenfall.ai/models/topaz-labs/topaz-image-upscale/gallery
- Playground: https://lumenfall.ai/playground?model=topaz-image-upscale
- API Documentation: https://docs.lumenfall.ai