Topaz Upscale

Name: Topaz Upscale
Author: Topaz Labs

topaz/upscale/image

Upscale Image is Topaz Labs's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

Use in agent Get API key

Base price: $0.08 / run
Execution: async
Model type: image
Input fields: 18

Try the model

Playground

Open playground

Input

Prompt(string)

Text prompt to guide generative upscaling (max 1024 chars). Applies to Redefine model only.

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

Url of the image to be upscaled

This field is required.

Strength(number)

0.011

Enhancement strength (0.01-1.0). Applies to Text Refine model only. Range: 0.01 to 1.

Output Format(string)

Output format of the upscaled image. Allowed values: jpeg, png.

Face Enhancement Creativity(number)

Creativity level for face enhancement. 0.0 means no creativity, 1.0 means maximum creativity. Ignored if face enhancement is disabled. Range: 0 to 1.

Enhancement Model(string)

Model to use for image enhancement. Allowed values: Low Resolution V2, Standard V2, CGI, High Fidelity V2, Text Refine, Recovery, Redefine, Recovery V2, Standard MAX, Wonder.

Subject Detection(string)

Subject detection mode for the image enhancement. Applies to standard enhance and Recovery V2 models. Allowed values: All, Foreground, Background.

Crop To Fill(boolean)

Fix Compression(number)

Compression artifact removal level (0.0-1.0). Applies to Standard V2, Low Resolution V2, High Fidelity V2, and Text Refine models. Range: 0 to 1.

Face Enhancement Strength(number)

Strength of the face enhancement. 0.0 means no enhancement, 1.0 means maximum enhancement. Ignored if face enhancement is disabled. Range: 0 to 1.

Detail(number)

Detail recovery level (0.0-1.0). Applies to Recovery V2 model only. Range: 0 to 1.

Creativity(integer)

Creativity level for generative upscaling (1-6). Higher values produce more creative/hallucinated details. Applies to Redefine model only. Range: 1 to 6.

Autoprompt(boolean)

Enable automatic prompt generation for generative upscaling. Applies to Redefine model only.

Sharpen(number)

Sharpening level (0.0-1.0). Applies to Standard V2, Low Resolution V2, CGI, High Fidelity V2, Text Refine, and Redefine models. Range: 0 to 1.

Upscale Factor(number)

Factor to upscale the image by (e.g. 2.0 doubles width and height) Range: 1 to 4.

Texture(integer)

Texture detail level for generative upscaling (1-5). Applies to Redefine model only. Range: 1 to 5.

Denoise(number)

Denoising level (0.0-1.0). Applies to Standard V2, Low Resolution V2, CGI, High Fidelity V2, Text Refine, and Redefine models. Range: 0 to 1.

Face Enhancement(boolean)

Whether to apply face enhancement to the image. Applies to standard enhance and Recovery V2 models.

OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price: $0.08 / run
Billing formula: ((usage.width ?? 0) * (usage.height ?? 0) / 1000000) <= 0 ? 1.36 : ((usage.width * usage.height / 1000000) <= 24 ? 0.08 : ((usage.width * usage.height / 1000000) <= 48 ? 0.16 : ((usage.width * usage.height / 1000000) <= 96 ? 0.32 : 1.36)))

Context & modalities

Input: Schema-defined
Output: image

Capabilities

Chat: Not supported
Vision: Not supported
Reasoning: Not supported
Structured output: Not supported
Function calling: Not supported
Audio input: Not supported

Access

Provider: Topaz Labs
Model ID: topaz/upscale/image
Execution: async
API: Unified Run API
Endpoint: /v1/run

API README

Topaz Upscale

Topaz Upscale is an image restoration and enlargement workflow for turning a small, soft, compressed, or noisy source into a cleaner high-resolution asset. Rather than merely resizing pixels, it applies a selected enhancement model and adjustable recovery controls to rebuild useful detail for the intended output size.

The route can handle conventional photographic restoration as well as generative re-interpretation when Redefine is selected. Choose the enhancement model to match the source, then balance denoise, sharpening, detail, compression repair, face enhancement, and upscale factor so the result improves without looking overprocessed.

Highlights

Model-specific restoration. Selects specialized enhancement behavior for low-resolution photos, CGI, text, high-fidelity sources, recovery, or generative reinterpretation.
Up to 4× enlargement. Scales the image while rebuilding detail instead of relying on a simple interpolation pass.
Artifact and noise cleanup. Combines denoise, compression repair, sharpening, texture, and detail controls for damaged or web-sourced assets.
Face-aware enhancement. Offers subject detection and dedicated facial recovery controls for portraits and group imagery.

Pricing

Configuration	Billing unit	Price
Output up to 24 MP	Per image	$0.08
Output over 24 MP to 48 MP	Per image	$0.16
Output over 48 MP to 96 MP	Per image	$0.32
Output over 96 MP or fallback	Per image	$1.36

When to Use

✅ Good fit	❌ Consider alternatives
The project needs restoring and enlarging an existing image	The goal is a different media task or endpoint
The available inputs match the required local schema	Required source media or permissions are unavailable
The brief can specify subject, composition, style, and delivery	The result must be deterministic at pixel or sample level
The supported formats and controls match final placement	Delivery requires unsupported dimensions, codecs, or duration
An asynchronous generated result fits the workflow	A live, frame-synchronous, or real-time response is mandatory

Prompt Guide

Write the request as a production brief: identify the main subject or source material, state the intended transformation, describe composition or timing, and finish with style, atmosphere, and delivery constraints. Keep preservation requirements separate from requested changes, and use only fields exposed by this route.

{
  "prompt": "A cinematic, precisely directed scene with clear subject action, camera movement, lighting, and atmosphere",
  "image": "https://example.com/reference.jpg",
  "detail": 0,
  "denoise": 0,
  "sharpen": 0
}

Technical Specs

Spec	Value
Model ID	`topaz/upscale/image`
Input fields	`image` (string)<br>`detail` (number; 0–1)<br>`prompt` (string)<br>`denoise` (number; 0–1)<br>`sharpen` (number; 0–1)<br>`texture` (integer; 1–5)<br>`strength` (number; 0.01–1)<br>`autoprompt` (boolean)<br>`creativity` (integer; 1–6)<br>`crop_to_fill` (boolean)<br>`output_format` (string; `jpeg`, `png`)<br>`upscale_factor` (number; 1–4)<br>`fix_compression` (number; 0–1)<br>`face_enhancement` (boolean)<br>`enhancement_model` (string; `Low Resolution V2`, `Standard V2`, `CGI`, `High Fidelity V2`, `Text Refine`, `Recovery`, `Redefine`, `Recovery V2`, `Standard MAX`, `Wonder`)<br>`subject_detection` (string; `All`, `Foreground`, `Background`)<br>`face_enhancement_strength` (number; 0–1)<br>`face_enhancement_creativity` (number; 0–1)
Required input	`prompt`, `image`
Output fields	`url`, `content_type`
Execution	Asynchronous job

Related Models

topaz/upscale/image/generative
topaz/upscale/image/creative
topaz/restore/image

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Endpoint

https://api.sandbase.ai/v1/run

Model ID

topaz/upscale/image

# Preserve Unicode and shell metacharacters in the request body.
result=$(printf '%s' 'ewogICJtb2RlbCI6ICJ0b3Bhei91cHNjYWxlL2ltYWdlIiwKICAiaW1hZ2UiOiAiaHR0cHM6Ly9zdGF0aWMuc2FuZGJhc2UuYWkvZXhhbXBsZXMvdG9wYXovdXBzY2FsZS9pbWFnZS9pbnB1dF9pbWFnZV8wLmpwZWciLAogICJjcm9wX3RvX2ZpbGwiOiBmYWxzZSwKICAib3V0cHV0X2Zvcm1hdCI6ICJqcGVnIiwKICAidXBzY2FsZV9mYWN0b3IiOiAyLAogICJmYWNlX2VuaGFuY2VtZW50IjogdHJ1ZSwKICAiZW5oYW5jZW1lbnRfbW9kZWwiOiAiU3RhbmRhcmQgVjIiLAogICJzdWJqZWN0X2RldGVjdGlvbiI6ICJBbGwiLAogICJmYWNlX2VuaGFuY2VtZW50X3N0cmVuZ3RoIjogMC44LAogICJmYWNlX2VuaGFuY2VtZW50X2NyZWF0aXZpdHkiOiAwCn0=' \
  | base64 --decode \
  | curl --fail-with-body --silent \
      -X POST "https://api.sandbase.ai/v1/run" \
      -H "Authorization: Bearer $SANDBASE_API_KEY" \
      -H "Content-Type: application/json" \
      --data-binary @-)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models

Model	Context	Input / 1M	Output / 1M	Released
Topaz UpscaleThis model `Topaz Labs`	—	—	—	Jun 27, 2025
Topaz Upscale Image Creative `Topaz Labs`	—	—	—	Aug 17, 2026
Topaz Upscale Image Generative `Topaz Labs`	—	—	—	Aug 17, 2026
Topaz Upscale Image Precision `Topaz Labs`	—	—	—	Aug 17, 2026
Topaz Upscale Image Transparent `Topaz Labs`	—	—	—	Aug 17, 2026
Topaz Adjust Image `Topaz Labs`	—	—	—	Aug 17, 2026