Topaz Video Upscale API Documentation

Topaz Video Upscale API Documentation

Playground

Try it on WaveSpeedAI!

Topaz Video Upscale upscales and enhances video up to 4K with Topaz’s precision Proteus, Artemis, Gaia, Theia, Iris and Dione models. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Topaz Video Upscale upscales and enhances video up to 4K with Topaz’s precision Proteus, Artemis, Gaia, Theia, Iris and Dione 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
    21 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: Proteus.
target_resolutionNoTarget resolution to upscale to. The source aspect ratio is preserved. Options: 720p, 1080p, 2k, 4k. Default: 1080p.

Models

ModelBest for
ProteusThe default choice for video enhancement and upscaling (default).
Proteus NaturalNext-generation natural enhancement; always upscales 2x.
RheaHigh-fidelity upscaling for fine detail.
Artemis High QualityEnhancement for high-quality sources.
Artemis Medium QualityBalanced enhancement for medium-quality footage.
Artemis Low QualityHeavier restoration for low-quality footage.
Artemis Medium HaloRemoves moderate edge haloing.
Artemis Strong HaloRemoves pronounced edge haloing.
Artemis Aliasing & MoireReduces aliasing and moire.
Gaia High QualityFine detail for already-clean sources.
Gaia CGUpscaling for animation, CG and stylized footage.
Gaia 2 AnimationAnimation upscaling; always upscales 2x.
Theia Fine Tune DetailAggressive per-frame detail enhancement.
Theia Fine Tune FidelityStable, consistent detail with high fidelity.
Iris Medium QualityFace recovery for mid-quality footage.
Iris Low QualityFace recovery for degraded footage.
Dione DVDeinterlacing for DV sources.
Dione TVDeinterlacing for TV sources.
Dione RobustDeinterlacing for challenging interlaced content.
Dione DehaloDeinterlacing plus halo removal.
Dione Robust DehaloRobust deinterlacing plus halo removal.

Pricing

$0.20 per gigapixel processed, where gigapixels = (width × step) × (height × step) × frames ÷ 1024³ and the step is 1 for a scale up to 1.2x, 2 up to 2.4x and 4 above. Gaia 2 Animation: $0.10 per 300 frames up to 1080p output, per 100 frames above. 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 Proteus 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": "Proteus",
  "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" \
  -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.
modelstringNoProteusProteus, Proteus Natural, Rhea, Artemis High Quality, Artemis Medium Quality, Artemis Low Quality, Artemis Medium Halo, Artemis Strong Halo, Artemis Aliasing & Moire, Gaia High Quality, Gaia CG, Gaia 2 Animation, Theia Fine Tune Detail, Theia Fine Tune Fidelity, Iris Medium Quality, Iris Low Quality, Dione DV, Dione TV, Dione Robust, Dione Dehalo, Dione Robust DehaloThe Topaz model to use. Proteus: The default choice for video enhancement and upscaling (default). Proteus Natural: Next-generation natural enhancement; always upscales 2x. Rhea: High-fidelity upscaling for fine detail. Artemis High Quality: Enhancement for high-quality sources. Artemis Medium Quality: Balanced enhancement for medium-quality footage. Artemis Low Quality: Heavier restoration for low-quality footage. Artemis Medium Halo: Removes moderate edge haloing. Artemis Strong Halo: Removes pronounced edge haloing. Artemis Aliasing & Moire: Reduces aliasing and moire. Gaia High Quality: Fine detail for already-clean sources. Gaia CG: Upscaling for animation, CG and stylized footage. Gaia 2 Animation: Animation upscaling; always upscales 2x. Theia Fine Tune Detail: Aggressive per-frame detail enhancement. Theia Fine Tune Fidelity: Stable, consistent detail with high fidelity. Iris Medium Quality: Face recovery for mid-quality footage. Iris Low Quality: Face recovery for degraded footage. Dione DV: Deinterlacing for DV sources. Dione TV: Deinterlacing for TV sources. Dione Robust: Deinterlacing for challenging interlaced content. Dione Dehalo: Deinterlacing plus halo removal. Dione Robust Dehalo: Robust deinterlacing plus halo removal.
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.