Topaz Video Upscale Generative API Documentation

Topaz Video Upscale Generative API Documentation

Playground

Try it on WaveSpeedAI!

Topaz Video Upscale Generative restores and upscales real and AI-generated video with Topaz Starlight diffusion models. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Topaz Video Upscale Generative restores and upscales real and AI-generated video with Topaz Starlight diffusion models, powered by Topaz Labs models.


Why Choose This?

  • Professional Topaz quality
    The same models used by photographers, filmmakers and studios.

  • Choose the right model
    10 Topaz models, each tuned for a different kind of video.

  • Pay for what you process
    Pricing follows the size of the output, matching Topaz’s own rates.


Parameters

ParameterRequiredDescription
videoYesThe video to process.
modelNoThe Topaz model to use. Default: Starlight Precise 2.6.
target_resolutionNoTarget resolution to upscale to. The source aspect ratio is preserved. Options: 720p, 1080p, 2k, 4k. Default: 1080p.

Models

ModelBest for
Starlight Precise 2.6High-quality generative upscaling and enhancement up to 4K (default; up to 9000 frames).
Starlight Precise 2.5Improved realism for AI-generated video (up to 9000 frames).
Starlight Precise 2Natural realism for GenAI video (up to 450 frames).
Starlight Precise 1First-generation precise diffusion upscaling (up to 9000 frames).
Starlight Fast 3The fastest Starlight model (up to 9000 frames).
Starlight Fast 2Fast diffusion upscaling with higher fidelity.
Starlight Fast 1First-generation fast generative upscaling (up to 9000 frames).
Starlight HQMaximum-quality generative enhancement for modern high-resolution footage.
Starlight MiniDiffusion restoration for archival and degraded footage.
Starlight SharpFast restoration with sharper detail.

Pricing

Priced per output frame. Up to 1080p output: $0.10 per 26.04 frames (Starlight Precise 1: per 10 frames; Starlight Fast 1 and 2: per 52.08 frames). Above 1080p: $0.10 per 11.92 frames (Starlight Precise 1: per 6.02 frames; Starlight Fast 1 and 2: per 23.84 frames). Minimum $0.10.


How to Use

  1. Upload your video — Provide a URL or upload a file.
  2. Pick a model — Start with the default Starlight Precise 2.6 and switch if your content needs it.
  3. Choose the target resolution — 720p, 1080p, 2k, 4k.
  4. Submit — Download the result when it is ready.

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'
{
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
  "model": "Starlight Precise 2.6",
  "target_resolution": "1080p"
}
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/video/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
videostringYes-The video to process.
modelstringNoStarlight Precise 2.6Starlight Precise 2.6, Starlight Precise 2.5, Starlight Precise 2, Starlight Precise 1, Starlight Fast 3, Starlight Fast 2, Starlight Fast 1, Starlight HQ, Starlight Mini, Starlight SharpThe Topaz model to use. Starlight Precise 2.6: High-quality generative upscaling and enhancement up to 4K (default; up to 9000 frames). Starlight Precise 2.5: Improved realism for AI-generated video (up to 9000 frames). Starlight Precise 2: Natural realism for GenAI video (up to 450 frames). Starlight Precise 1: First-generation precise diffusion upscaling (up to 9000 frames). Starlight Fast 3: The fastest Starlight model (up to 9000 frames). Starlight Fast 2: Fast diffusion upscaling with higher fidelity. Starlight Fast 1: First-generation fast generative upscaling (up to 9000 frames). Starlight HQ: Maximum-quality generative enhancement for modern high-resolution footage. Starlight Mini: Diffusion restoration for archival and degraded footage. Starlight Sharp: Fast restoration with sharper detail.
target_resolutionstringNo1080p720p, 1080p, 2k, 4kTarget resolution to upscale to. The source aspect ratio is preserved.

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.