by Topaz Labs

Upscale to 4K, remove noise or blur, convert to HDR, smooth or slow down motion

topaz/video-ai/upscale
  • Up to 4K
  • Upscale Video
  • Video Enhancer
  • Slow Motion

About Topaz Video AI

Upscale to 4K, remove noise or blur, convert to HDR, smooth or slow down motion.

Call it with the model name topaz/video-ai/upscale on POST /jobs/createTask, from $0.00706.

Introduction

Video AI’s enlargement tool is for a small recording that needs a larger place in an edit: an interview insert, a phone clip or an animated scene. It offers source-specific processing rather than a single look, so a face-damaged transfer and a clean computer-rendered shot need not receive the same treatment.

Key features

The 21-model selection covers general enhancement, several degrees of source damage, edge halos, repeating interference and interlacing. Proteus provides the initial setting, Rhea focuses on faithful detail, and Iris addresses faces in degraded material. Dione is relevant when alternating scan lines are part of the recording rather than ordinary blur.

The podcast trial expanded a five-second 640×360 shot into a 1920×1080 file without losing its microphone audio or 24 fps timing. In the street trial, bicycle contours became easier to read but block-shaped compression remained in places. The result demonstrates useful enlargement while leaving a visible ceiling on what the damaged input can support.

Request parameters

ParameterRequiredDescription
presetNoChoose from the presets available for this model. proteus · proteus_natural · rhea · artemis_hq · artemis_mq · artemis_lq · artemis_medium_halo · artemis_strong_halo · artemis_aliasing_moire · gaia_hq · gaia_cg · gaia_2_animation · theia_detail · theia_fidelity · iris_mq · iris_lq · dione_dv · dione_tv · dione_robust · dione_dehalo · dione_robust_dehalo · Default: proteus
resolutionNoChoose an available output size. 720p · 1080p · 2k · 4k · Default: 1080p
video_urlYesThe clip to work on.

Pricing

Prices are in USD. The API uses a separate USD balance. Website credits cannot be used or transferred to it, and API funds cannot be transferred to website credits. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

OptionUSD per second
preset artemis aliasing moire · resolution 720p$0.00706
preset artemis hq · resolution 720p$0.00706
preset artemis lq · resolution 720p$0.00706
preset artemis medium halo · resolution 720p$0.00706
preset artemis mq · resolution 720p$0.00706
preset artemis strong halo · resolution 720p$0.00706
preset dione dehalo · resolution 720p$0.00706
preset dione dv · resolution 720p$0.00706
preset dione robust · resolution 720p$0.00706
preset dione robust dehalo · resolution 720p$0.00706
preset dione tv · resolution 720p$0.00706
preset gaia cg · resolution 720p$0.00706

Send the same request body to POST /jobs/quote to see the estimated and maximum USD charge before running. A quote does not run the task or charge your balance.

Use cases

For a talking-head compilation, process a short answer that includes both facial movement and the microphone. This exposes problems that a still portrait would conceal, including edges that change as the speaker turns.

For a mixed-media sequence, separate animation from old DV material before testing. Gaia’s animation options and Dione’s interlace treatments address different source structures; one choice across the entire sequence can miss the reason a particular shot looks poor.

Prompt guide & pro tips

There is no prompt field for this operation. Start with proteus at 1080p, inspect a representative section and change the model according to the visible problem.

Check the returned dimensions before conforming the shot, especially with the two presets that always double width and height. Compare thin lines, eyes and hair at the intended display size, then play the whole take with sound. Keep the input beside the output during approval so sharper contours are not mistaken for complete removal of compressed texture.

API quick start

Call the Topaz Video AI API in three steps

  1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow-. API calls use your separate USD balance.
  2. Send the request. POST /jobs/createTask with model topaz/video-ai/upscale and an input object that follows the parameter table. The response returns a task ID straight away.
  3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "topaz/video-ai/upscale",
  "input": {
    "video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
    "preset": "proteus",
    "resolution": "1080p"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Topaz Video AI API questions

How much does the Topaz Video AI API cost?

Topaz Video AI starts at $0.002 per second with Slow Motion, its cheapest task. Prices for Upscale Video by option: artemis aliasing moire · 720p $0.00706 per second, artemis hq · 720p $0.00706 per second, artemis lq · 720p $0.00706 per second, artemis medium halo · 720p $0.00706 per second. The API uses a separate USD balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

What is the model name for Topaz Video AI in the API?

Put topaz/video-ai/upscale for Upscale Video; topaz/video-ai/video-edit for Video Enhancer; topaz/video-ai/frame-interpolation for Slow Motion in the model field of POST /jobs/createTask.

What happens to the audio?

Enhancement and ordinary frame-rate conversion keep the sound; the tested slowed clips omit it, so a slow-motion edit needs its own audio treatment.

How do I choose the settings?

Use Proteus for a general enlargement trial, Nyx for grain or Apollo for retiming; specialize only after inspecting the defect in the source.

What are the limits of the Topaz Video AI API?

Resolutions: 720p · 1080p · 2K · 4K; Longest input clip: 60 s. Requests outside these limits are rejected before anything is charged.

Can I try Topaz Video AI without writing code?

Run Topaz Video AI in the Playground with your API USD balance, without an API key. Each run appears in your developer history with its matching code.

All Topaz models

More about Topaz Video AI