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
| Parameter | Required | Description |
|---|---|---|
| video | Yes | The video to process. |
| model | No | Processing model. Options: Starlight Precise 2.6, Starlight Precise 2.5, Starlight Fast 3, Starlight Fast 2, Starlight Mini. Default: Starlight Precise 2.6. |
| target_resolution | No | Target resolution to upscale to. The source aspect ratio is preserved. Options: 720p, 1080p, 2k, 4k. Default: 1080p. |
How to Use
- Upload your video — Provide a file or URL.
- Choose a model — Select the processing option for your input.
- Select a resolution — Choose the desired output tier.
- 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:
| Model | 720p | 1080p | 2k | 4k |
|---|---|---|---|---|
| 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
doneRetry temporary errors only while polling, never the submit request. Errors, retries and timeouts
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| video | string | Yes | - | The video to process. | |
| model | string | No | Starlight Precise 2.6 | Starlight Precise 2.6, Starlight Precise 2.5, Starlight Fast 3, Starlight Fast 2, Starlight Mini | The 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_resolution | string | No | 1080p | 720p, 1080p, 2k, 4k | Target 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
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Task status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses. |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<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.urls | object | Object containing related API endpoints |
| data.status | string | Status: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |