Skip to navigation
ImagesUpscale

Upscale with Topaz Text Refine

Upscale an image to 2x, 4x, or 8x its original resolution; no prompt is needed. Upload the source image using multipart/form-data. Returns results directly by default; set async or supply a webhook_url to get a generation_id and poll GET /v2/generations/{generation_id}.

Authentication

Api-Keystring

API key for access control. Use in the header with the name "Api-Key"

Query parameters

dry_runbooleanOptionalDefaults to false

When true, the request is validated and priced but not run: nothing is generated, stored, or billed, and no safety review is performed. The response is a PriceQuote object instead of the usual response for this endpoint. Send exactly the request you would send to generate, so the quote reflects the same options.

Request

A request to upscale one image with Topaz Text Refine. Upload the source image using multipart/form-data.

imagefileRequired
The source image to upscale, in a common format such as JPEG, PNG, or WEBP, up to 50MB. Multipart requests only. The uploaded image is used for this request only and is not stored.
upscale_factorenumOptionalDefaults to x2

How much to enlarge the source image: 2x, 4x, or 8x its original width and height. Rejected when the output would exceed 8192px on either side.

Allowed values:
strengthfloatOptional
Overall intensity of the enhancement model, from 0.01 to 1. Higher values look crisper but can turn unrealistic. Omit to let the model choose per image.
sharpenfloatOptional
Edge sharpening applied after enlarging, from 0 to 1. Omit to let the model choose per image.
denoisefloatOptional
Noise and grain reduction, from 0 to 1. Omit to let the model choose per image.
fix_compressionfloatOptional
Compression artifact removal, from 0 to 1. Omit to let the model choose per image.
face_enhancementbooleanOptional

Recover detail in faces. When true, face_enhancement_strength and face_enhancement_creativity are required.

face_enhancement_strengthfloatOptional
How strongly faces are recovered, from 0 to 1.
face_enhancement_creativityfloatOptional

How freely face recovery may reinterpret features, from 0 (faithful) to 1 (creative).

subject_detectionenumOptional
Where enhancements apply. Omit to let the model choose per image.
Allowed values:
seedintegerOptional0-2147483647
Random seed. Set for reproducible generation.
asyncbooleanOptionalDefaults to false

When false (the default), the request blocks until the upscaled image is ready and returns it in data. When true, the request returns as soon as it is accepted; poll GET /v2/generations/{generation_id} for the result.

webhook_urlstringOptionalformat: "uri"<=2048 characters

HTTPS URL that Ideogram delivers the generated result to. Ideogram sends a JSON POST to this URL once all images for the request have finished generating. The body mirrors the synchronous generate response: request_id, created, and a data array containing every generated image (url, prompt, resolution, seed, is_image_safe). Each delivery is signed with Ed25519 and verifiable against the public keys at https://api.ideogram.ai/v1/.well-known/jwks.json. Must be HTTPS; private and loopback hosts and the cloud metadata service are rejected.

Response

The upscaled image (synchronous requests), or an acknowledgement to poll with GET /v2/generations/{generation_id} (async requests).

generation_idstring

The generation ID to poll with GET /v2/generations/{generation_id}.

seedinteger0-2147483647
Random seed. Set for reproducible generation.
widthinteger
The output width in pixels.
heightinteger
The output height in pixels.
datalist of objectsOptional

The upscaled image. Present only for synchronous requests (async omitted or false).

Errors

400
Bad Request Error
401
Unauthorized Error
402
Payment Required Error
404
Not Found Error
429
Too Many Requests Error
500
Internal Server Error
503
Service Unavailable Error