by Topaz Labs

Remove noise or fix blur at the same resolution, up to 24 MP

topaz/denoise-sharpen/edit
  • Image Denoiser

About Topaz Denoise & Sharpen

Remove noise or fix blur at the same resolution, up to 24 MP.

Call it with the model name topaz/denoise-sharpen/edit on POST /jobs/createTask, from $0.12.

Introduction

Photo repair at original size

Apply Denoise Max, one of nine sharpening presets or Super Focus to a single photo of up to 24 MP, returning JPEG or PNG at the original size.

Repair request

{
  "image_url": "https://example.com/blurred-portrait.jpg",
  "preset": "denoise_normal",
  "output_format": "jpeg"
}

Current preset list

presetRepair target
denoise_normalDenoise Max; compatibility value and default
sharpen_standardGeneral sharpening
sharpen_strongStronger sharpening
sharpen_naturalNatural-looking sharpening
sharpen_portraitPortrait sharpening
sharpen_wildlifeWildlife sharpening
sharpen_refocusRefocusing fine detail
sharpen_motion_blurMotion blur
sharpen_lens_blurLens blur
sharpen_autoAutomatic separation of detail and noise
sharpen_super_focusGenerative reconstruction of severe blur

Results we inspected

Denoise Max removed most coloured speckle from the face, sweater and dark bar background in about 11 seconds. Hair and knit detail remain visible, while the skin looks smoother. The 2048×1152 dimensions did not change.

Our 1024×1536 café portrait lost most of its grain in roughly 20 seconds. Curls and sweater stitches remain readable; facial skin is smoother, so inspect the balance between clean surfaces and texture.

With sharpen_standard, the eyes, eyebrows and stubble become readable again at 1100×900. Inspect those reconstructed details at full size before using the portrait.

On the deliberately blurred bar portrait, Super Focus produced clearer eyes and stubble while keeping the man’s overall likeness. Auto Sharpen made a lighter adjustment and did not repair the severe defocus. Both tests took about 11 seconds.

Size and reconstruction limits

Each call applies one preset to one image of at most 24 MP. Output dimensions equal input dimensions. Denoise Max and Super Focus generate replacement detail and may smooth or alter texture. The former denoise_strong and denoise_extreme values have been removed; use denoise_normal for Denoise Max.

Request parameters

ParameterRequiredDescription
image_urlYesThe picture to start from.
output_formatNoFile type of the result. jpeg · png · Default: jpeg
presetNoChoose from the presets available for this model. denoise_normal · sharpen_standard · sharpen_strong · sharpen_natural · sharpen_portrait · sharpen_wildlife · sharpen_refocus · sharpen_motion_blur · sharpen_lens_blur · sharpen_auto · sharpen_super_focus · Default: denoise_normal

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 image
Standard$0.12

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.

API quick start

Call the Topaz Denoise & Sharpen 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/denoise-sharpen/edit 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/denoise-sharpen/edit",
  "input": {
    "image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
    "preset": "denoise_normal",
    "output_format": "jpeg"
  }
}'

# 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 Denoise & Sharpen API questions

How much does the Topaz Denoise & Sharpen API cost?

Topaz Denoise & Sharpen costs $0.12 per image. 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 Denoise & Sharpen in the API?

Put topaz/denoise-sharpen/edit for Image Denoiser in the model field of POST /jobs/createTask.

Why is Denoise Max called denoise_normal in requests?

The public value is retained for existing integrations. It now selects generative Denoise Max, rather than the retired Normal model.

What is the difference between Auto and Super Focus?

Auto Sharpen automatically separates detail from noise for sharpening. Super Focus reconstructs badly blurred detail; it was much more effective on our severely defocused test portrait.

What are the limits of the Topaz Denoise & Sharpen API?

Largest upload: 30 MB. Requests outside these limits are rejected before anything is charged.

Can I try Topaz Denoise & Sharpen without writing code?

Run Topaz Denoise & Sharpen 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 Denoise & Sharpen