> ## Documentation Index > Fetch the complete documentation index at: https://docs.unifically.com/llms.txt > Use this file to discover all available pages before exploring further. # Topaz Image Upscale > AI-powered image upscaling with selectable presets, face recovery, and per-preset tuning Upscale and enhance images using Topaz Labs AI models. Pick a preset for your source type, set an output size via `upscale_factor`, and optionally fine-tune the result through `extra_settings`. ## Model ``` topaz-labs/image-upscale ``` ## Parameters | Parameter | Type | Required | Default | Description | | ------------------ | ---------------- | -------- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `image_url` | string | Yes | - | Publicly-accessible URL of the source image | | `preset` | string | No | `standard-v2` | Topaz model variant. One of `standard-v2`, `low-resolution-v2`, `cgi`, `high-fidelity-v2`, `text-refine` | | `upscale_factor` | string \| number | No | - | Output-dimension multiplier. Accepts a number (e.g. `2`, `2.5`, `4`) or a string suffix (e.g. `"2x"`, `"4x"`). The source image is probed automatically to derive output dimensions | | `crop_to_fill` | boolean | No | `false` | Crop to fill output dimensions instead of letterboxing | | `face_enhancement` | boolean | No | `false` | Enable face recovery. When `true`, set `face_enhancement_strength` and `face_enhancement_creativity` inside `extra_settings` | | `output_format` | string | No | - | Output image format. One of `jpeg`, `jpg`, `png`, `tiff`, `tif` | | `extra_settings` | object | No | - | Model-specific tuning. See [Extra settings](#extra-settings) | Maximum output is **1024 MP** (megapixels). Requests whose computed output exceeds this are rejected pre-flight. ## Presets | Preset | Best for | | ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `standard-v2` (default) | General-purpose upscaling for most photos and graphics. Balances detail, sharpness, and noise reduction | | `low-resolution-v2` | Small, heavily compressed, or degraded inputs. Recovers usable detail from difficult sources | | `cgi` | Illustrations, digital art, renders, and stylised graphics. Preserves clean edges and flat colour regions. Adds `deblur_strength` | | `high-fidelity-v2` | Already high-resolution sources. Enlarges while preserving fine detail and natural texture without over-sharpening | | `text-refine` | Images with typography, logos, UI elements, and geometric shapes. Preserves edge clarity and shape accuracy. Adds `denoise_strength`, `deblur_strength`, `decompression_strength`, `opacity` | ## Extra settings Pass any of these inside `extra_settings`. Anything omitted is auto-configured by Topaz. ### Common (all presets) | Key | Type | Range | Description | | ----------------------------- | ------ | --------------------------------- | ----------------------------------------------------------------------- | | `face_enhancement_strength` | float | 0–1 | Required when `face_enhancement: true`. Strength of face recovery | | `face_enhancement_creativity` | float | 0–1 | Required when `face_enhancement: true`. `0` = realistic, `1` = creative | | `subject_detection` | string | `foreground`, `background`, `all` | Where enhancements are applied | | `sharpen` | float | 0–1 | Slightly sharpens the output | | `denoise` | float | 0–1 | Reduces noise | | `fix_compression` | float | 0–1 | Reduces JPEG compression artifacts | | `strength` | float | 0.01–1 | Overall model strength. Too high can look unrealistic | ### CGI-only | Key | Type | Range | Default | Description | | ----------------- | ----- | ----- | ------- | -------------------- | | `deblur_strength` | float | 0–1 | 0.5 | Deblur pass strength | ### Text Refine-only | Key | Type | Range | Default | Description | | ------------------------ | ----- | ----- | ------- | ------------------------------------------------ | | `denoise_strength` | float | 0–1 | 0.5 | Noise reduction strength | | `deblur_strength` | float | 0–1 | 0.5 | Deblur pass strength | | `decompression_strength` | float | 0–1 | 0.5 | Compression-artifact recovery strength | | `opacity` | float | 0–1 | 1.0 | Blend amount between source and processed output | ## Example - Basic upscale ```bash theme={null} curl -X POST https://api.unifically.com/v1/tasks \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_API_KEY" \ -d '{ "model": "topaz-labs/image-upscale", "input": { "image_url": "https://example.com/photo.jpg", "upscale_factor": "2x" } }' ``` ## Example - Recovering a low-resolution source ```bash theme={null} curl -X POST https://api.unifically.com/v1/tasks \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_API_KEY" \ -d '{ "model": "topaz-labs/image-upscale", "input": { "image_url": "https://example.com/old-photo.jpg", "preset": "low-resolution-v2", "upscale_factor": "4x", "extra_settings": { "fix_compression": 0.6, "denoise": 0.4 } } }' ``` ## Example - CGI / illustration ```bash theme={null} curl -X POST https://api.unifically.com/v1/tasks \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_API_KEY" \ -d '{ "model": "topaz-labs/image-upscale", "input": { "image_url": "https://example.com/illustration.png", "preset": "cgi", "upscale_factor": 2, "extra_settings": { "deblur_strength": 0.4 } } }' ``` ## Example - High-fidelity portrait with face recovery ```bash theme={null} curl -X POST https://api.unifically.com/v1/tasks \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_API_KEY" \ -d '{ "model": "topaz-labs/image-upscale", "input": { "image_url": "https://example.com/portrait.jpg", "preset": "high-fidelity-v2", "upscale_factor": "2x", "face_enhancement": true, "extra_settings": { "face_enhancement_strength": 0.7, "face_enhancement_creativity": 0.2, "subject_detection": "foreground" } } }' ``` ## Example - Text, logos, and UI screenshots ```bash theme={null} curl -X POST https://api.unifically.com/v1/tasks \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_API_KEY" \ -d '{ "model": "topaz-labs/image-upscale", "input": { "image_url": "https://example.com/screenshot.png", "preset": "text-refine", "upscale_factor": "2x", "output_format": "png", "extra_settings": { "decompression_strength": 0.7, "deblur_strength": 0.4, "opacity": 0.9 } } }' ``` ## Example - Fixed output framing with `crop_to_fill` ```bash theme={null} curl -X POST https://api.unifically.com/v1/tasks \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_API_KEY" \ -d '{ "model": "topaz-labs/image-upscale", "input": { "image_url": "https://example.com/photo.jpg", "upscale_factor": "4x", "crop_to_fill": true, "output_format": "png" } }' ``` ## Response ```json theme={null} { "code": 200, "success": true, "data": { "task_id": "abc123def456", "status": "pending" } } ```