Topaz Image Upscale Generative API Documentation

Topaz Image Upscale Generative API Documentation

Playground

Try it on WaveSpeedAI!

Topaz Image Upscale Generative upscales and restores images with Topaz Wonder, Recover, and Redefine models, improving resolution, reconstructing detail, and repairing low-quality imagery for creative assets, photography, design, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Topaz Image Upscale Generative enhances and upscales images with a choice of generative models.


Why Choose This?

  • Generative image upscaling — Add generated detail while enlarging the input.
  • Model selection — Choose from the available processing models.
  • Resolution options — Select an output resolution tier.

Parameters

ParameterRequiredDescription
imageYesThe image to process (JPEG, PNG, TIFF or WebP).
modelNoProcessing model. Options: Wonder 4, Wonder 3.5, Recover 3, Standard MAX, Redefine, Detail. Default: Wonder 4.
target_resolutionNoThe target resolution of the output: 2k (about 4 MP), 4k (about 16.8 MP) or 8k (about 67 MP). The source aspect ratio is preserved. Options: 2k, 4k, 8k. Default: 4k.
output_formatNoThe format of the output image. Options: jpeg, png. Default: jpeg.

How to Use

  1. Upload your image — Provide a file or URL.
  2. Choose a model — Select the processing option for your input.
  3. Select a resolution — Choose the desired output tier.
  4. Submit — Process and download the result.

Pricing

Pricing is per image, based on the selected resolution tier and model.

Model2k4k8k
Wonder 4 / Wonder 3.5$0.10$0.30$0.90
Recover 3 / Standard MAX / Redefine$0.20$0.50$1.70
Detail$0.10$0.10$0.30

Output format does not add a separate charge.


Notes

  • Resolution tiers are square-equivalent: 2k is about 2048 x 2048 pixels, 4k about 4096 x 4096, and 8k about 8192 x 8192.
  • Actual width and height vary with the source aspect ratio.
  • Generative processing can change fine details; review the result for your intended use.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "model": "Wonder 4",
  "target_resolution": "4k",
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/topaz/image/upscale-generative" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Retry temporary errors only while polling, never the submit request. Errors, retries and timeouts

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
imagestringYes-The image to process (JPEG, PNG, TIFF or WebP).
modelstringNoWonder 4Wonder 4, Wonder 3.5, Recover 3, Standard MAX, Redefine, DetailThe Topaz model to use. Wonder 4: The most advanced all-purpose generative enhancement and upscaling (default). Wonder 3.5: High-quality generative upscaling with great realism. Recover 3: Recovers rich detail in heavily degraded images. Standard MAX: High-quality upscaling with generative detail. Redefine: Adds new generative detail, guided by an automatic description. Detail: Improves realism in AI-generated faces.
target_resolutionstringNo4k2k, 4k, 8kThe target resolution of the output: 2k (about 4 MP), 4k (about 16.8 MP) or 8k (about 67 MP). The source aspect ratio is preserved.
output_formatstringNojpegjpeg, pngThe format of the output image.

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.statusstringTask status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses.
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.statusstringStatus: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.