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 videos with Topaz Starlight diffusion models, reconstructing detail and improving visual quality for low-resolution footage, generative video, restoration, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Topaz Video Upscale Generative uses Starlight models to enhance and upscale video with generated detail.


Why Choose This?

  • Generative video 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
videoYesThe video to process.
modelNoProcessing model. Options: Starlight Precise 2.6, Starlight Precise 2.5, Starlight Fast 3, Starlight Fast 2, Starlight Mini. Default: Starlight Precise 2.6.
target_resolutionNoTarget resolution to upscale to. The source aspect ratio is preserved. Options: 720p, 1080p, 2k, 4k. Default: 1080p.

How to Use

  1. Upload your video — 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 calculated upfront from the source video duration and selected resolution and processing model. The source duration is rounded up to the next whole second, capped at 300 seconds for billing. The minimum charge is $0.10, and the total is rounded up to the next $0.10.

Example Costs

For a 10-second source video:

Model720p1080p2k4k
Starlight Precise 2.6 / Starlight Precise 2.5 / Starlight Fast 3 / Starlight Mini$1.20$1.20$2.60$2.60
Starlight Fast 2$0.60$0.60$1.30$1.30

Examples use the selected resolution and a billing basis of 30 source frames per second. Other durations have different totals; the displayed price is calculated before submission.


Notes

  • Use source clips up to 300 seconds.
  • The source aspect ratio is retained when selecting a resolution.
  • 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'
{
  "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 Fast 3, Starlight Fast 2, Starlight MiniThe Topaz model to use. Starlight Precise 2.6: High-quality generative upscaling and enhancement up to 4K (default). Starlight Precise 2.5: Improved realism for AI-generated video. Starlight Fast 3: The fastest Starlight model. Starlight Fast 2: Fast diffusion upscaling with higher fidelity. Starlight Mini: Diffusion restoration for archival and degraded footage.
target_resolutionstringNo1080p720p, 1080p, 2k, 4kTarget resolution to upscale to. The source aspect ratio is preserved.

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.