topaz/upscale/image/generative
Upscale Image Generative by Topaz Labs - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.
Input
Text prompt to guide generative upscaling (max 1024 chars). Applies to Redefine model only.
Url of the image to be upscaled
Output format of the upscaled image. Allowed values: jpeg, png.
01
Detail recovery level (0.0-1.0). Applies to Recovery V2 model only. Range: 0 to 1.
Subject detection mode for the image enhancement. Applies to Wonder 3, Recovery and Recovery V2 models. Allowed values: All, Foreground, Background.
14
Factor to upscale the image by (e.g. 2.0 doubles width and height) Range: 1 to 4.
Enable automatic prompt generation for generative upscaling. Applies to Redefine model only.
Whether to apply face enhancement to the image.
01
Sharpening level (0.0-1.0). Applies to Redefine model only. Range: 0 to 1.
01
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.
16
Creativity level for generative upscaling (1-6). Higher values produce more creative/hallucinated details. Applies to Redefine model only. Range: 1 to 6.
Enhancement strength for generative upscaling. Applies to Wonder 3 and Wonder 3.5 models. When omitted, Topaz auto-configures it. Allowed values: low, medium, high.
01
Denoising level (0.0-1.0). Applies to Redefine model only. Range: 0 to 1.
01
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.
15
Texture detail level for generative upscaling (1-5). Applies to Redefine model only. Range: 1 to 5.
Generative upscaling model. Wonder 3.5 is the latest Wonder with finer detail and fewer repetitive patterns; Wonder 3 is Topaz's most advanced generative realism model (Wonder 2/Wonder are earlier generations); Recover 3 rebuilds natural detail; Standard MAX is high-quality precision-leaning upscaling; Redefine adds prompt-guided creative detail; Recovery and Recovery V2 rebuild extreme low-resolution images. Allowed values: Wonder 3.5, Wonder 3, Wonder 2, Wonder, Recover 3, Standard MAX, Redefine, Recovery V2, Recovery.
Idle
Example output — click Run to generate your own
Production endpoint
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
POST
https://api.sandbase.ai/v1/runModel ID
topaz/upscale/image/generative01
Input Schema
17 parameters · 2 required · 15 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Required | Url of the image to be upscaled · Min length: 1 |
prompt | string | Required | Text prompt to guide generative upscaling (max 1024 chars). Applies to Redefine model only. · Max length: 1024 |
model | string | Optional | Generative upscaling model. Wonder 3.5 is the latest Wonder with finer detail and fewer repetitive patterns; Wonder 3 is Topaz's most advanced generative realism model (Wonder 2/Wonder are earlier generations); Recover 3 rebuilds natural detail; Standard MAX is high-quality precision-leaning upscaling; Redefine adds prompt-guided creative detail; Recovery and Recovery V2 rebuild extreme low-resolution images. · Options: Wonder 3.5, Wonder 3, Wonder 2, Wonder, Recover 3, Standard MAX, Redefine, Recovery V2, Recovery · Default: "Wonder 3" Wonder 3.5Wonder 3Wonder 2WonderRecover 3Standard MAXRedefineRecovery V2Recovery |
detail | number | Optional | Detail recovery level (0.0-1.0). Applies to Recovery V2 model only. · Min: 0 · Max: 1 |
denoise | number | Optional | Denoising level (0.0-1.0). Applies to Redefine model only. · Min: 0 · Max: 1 |
sharpen | number | Optional | Sharpening level (0.0-1.0). Applies to Redefine model only. · Min: 0 · Max: 1 |
texture | integer | Optional | Texture detail level for generative upscaling (1-5). Applies to Redefine model only. · Min: 1 · Max: 5 |
autoprompt | boolean | Optional | Enable automatic prompt generation for generative upscaling. Applies to Redefine model only. |
creativity | integer | Optional | Creativity level for generative upscaling (1-6). Higher values produce more creative/hallucinated details. Applies to Redefine model only. · Min: 1 · Max: 6 |
crop_to_fill | boolean | Optional | Default: false |
output_format | string | Optional | Output format of the upscaled image. · Options: jpeg, png · Default: "jpeg" jpegpng |
upscale_factor | number | Optional | Factor to upscale the image by (e.g. 2.0 doubles width and height) · Min: 1 · Max: 4 · Default: 2 |
face_enhancement | boolean | Optional | Whether to apply face enhancement to the image. · Default: true |
subject_detection | string | Optional | Subject detection mode for the image enhancement. Applies to Wonder 3, Recovery and Recovery V2 models. · Options: All, Foreground, Background · Default: "All" AllForegroundBackground |
enhancement_strength | string | Optional | Enhancement strength for generative upscaling. Applies to Wonder 3 and Wonder 3.5 models. When omitted, Topaz auto-configures it. · Options: low, medium, high lowmediumhigh |
face_enhancement_strength | number | Optional | Strength of the face enhancement. 0.0 means no enhancement, 1.0 means maximum enhancement. Ignored if face enhancement is disabled. · Min: 0 · Max: 1 · Default: 0.8 |
face_enhancement_creativity | number | Optional | Creativity level for face enhancement. 0.0 means no creativity, 1.0 means maximum creativity. Ignored if face enhancement is disabled. · Min: 0 · Max: 1 · Default: 0 |
02
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
03
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "Wonder 3",
"image": "https://static.sandbase.ai/examples/topaz/upscale/image/generative/input_image_0.jpeg",
"crop_to_fill": false,
"output_format": "jpeg",
"upscale_factor": 2,
"face_enhancement": true,
"subject_detection": "All",
"face_enhancement_strength": 0.8,
"face_enhancement_creativity": 0,
"prompt": "a beautiful sunset over mountains"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"