Video Face EnhancerAbout Video Face Enhancer
The Video Face Enhancer API is one video-edit endpoint, popnow/face-enhancer-video-v1/video-edit. It takes an MP4 and returns the same clip with up to three faces per frame restored, largest first, and kept steady from frame to frame. Length, frame rate, resolution and the audio track are preserved, so the output can drop into an existing edit without re-timing anything.
Call it with the model name popnow/face-enhancer-video-v1/video-edit on POST /jobs/createTask, from $0.012.
Introduction
Video Face Enhancer restores and sharpens the faces in every frame of a clip. You send video_url; the tool finds up to three faces per frame, largest first, and rebuilds the detail that heavy compression or softness took away, keeping the result steady from one frame to the next. Motion, framing, length and the original audio track stay as they were, and the clip comes back at the resolution you sent. Accepted clips are MP4 files from 3 seconds to 5 minutes long, and there is no prompt.
Key features
Faces cleaned in every frame
The restoration runs on the whole clip, not on a single still. In our test we took a 5-second 640×360 clip of a podcast host and degraded it with heavy H.264 compression. It came back at 640×360 and 24 fps, still 5.0 seconds long, after about 21 seconds of processing. Eyes, teeth and the hairline were sharper in every frame and did not flicker, and the host was still recognisably the same person.
Everything else stays as it was
Audio, motion, framing and length are kept, and the area around the faces is left alone: the room behind the host was unchanged. The tool does not enlarge the video. If you need more pixels as well, use Video Upscaler (/api/video-upscaler-v1).
Request parameters
| Parameter | Required | Description |
|---|---|---|
video_url | Yes | The 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.
| Option | USD per second |
|---|---|
| Standard | $0.012 |
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
Podcast and interview clips
Talking-head footage that has been compressed hard for upload loses detail in the face first. Run the clip through once to bring back eyes, teeth and hairline while the room, the camera framing and the sound stay the same.
Old or over-compressed footage
Clips that were saved, shared and re-encoded several times look soft and blocky around the face. Up to three faces per frame are restored, largest first, so a clip with one or two clear speakers is the best fit.
Footage you plan to enlarge later
Clean the faces first, then use Video Upscaler (/api/video-upscaler-v1) if the clip also needs more pixels for a larger screen.
Prompt guide & pro tips
There is no prompt: choose the clip
The single input is video_url, an MP4 upload or a public link, 3 seconds to 5 minutes long.
Pick faces that can be recovered
Real human faces that are reasonably large and clearly visible improve the most. If a clip shows more than three faces at once, the three largest are restored and the rest are left as they were.
Check the result against the source
Watch the output at normal speed and on a paused frame, and check the audio, the length and the frame rate as well as the faces. The image version of this tool left skin a little smoother than a real photo would be, so look for the same softening on faces in motion. The background is not touched, so any compression blocks there remain. Keep the source file.
API quick start
Call the Video Face Enhancer API in three steps
- 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.
- Send the request. POST /jobs/createTask with model popnow/face-enhancer-video-v1/video-edit and an input object that follows the parameter table. The response returns a task ID straight away.
- 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: $IDEMPOTENCY_KEY" \
-d '{
"model": "popnow/face-enhancer-video-v1/video-edit",
"input": {
"video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4"
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$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.
What to build with the Video Face Enhancer API
- A clean-up pass for generated video, running each finished clip through the enhancer before it reaches the user.
- An archive product that restores old family or interview footage in batches, one clip per job.
- A post-production step in a longer pipeline, placed after the edit and before delivery.
Video Face Enhancer parameter notes
- video_url is the only field: an MP4 upload or a public URL. The clip must be between 3 seconds and 5 minutes long. Outside that range the request is refused before any charge.
- There is no prompt, no resolution option and no audio switch. Length, motion, framing, size and the original audio all stay as they are.
- Faces that are reasonably large and clearly visible gain the most. Very small faces in a wide shot improve less, so a closer shot restores better.
How Video Face Enhancer API pricing adds up
Billed in USD per second of input at $0.012 per second, rounded up to the next whole second with a 3-second minimum, so the smallest job costs $0.036. The cap is 300 seconds, which is $3.60 at most. An uploaded file is held at its own length and a URL at the 5-minute maximum until delivery, and the difference is released once the job finishes. Failed requests are not charged, and API usage is paid from the separate API balance.
- Video Face Enhancer, 5-second clip: $0.06 each, $6.00 for 100 clips
Async jobs, webhooks and rate limits
Every Video Face Enhancer request is asynchronous: createTask returns a taskId straight away, and the result arrives when the job finishes. Poll GET /jobs/recordInfo every few seconds, or pass a public https callBackUrl and verify the X-Webhook-Signature header (HMAC-SHA256 over taskId, timestamp and the body hash) before trusting the payload. Each account gets 1,000 write requests per 10 seconds; a 429 carries Retry-After. Send an Idempotency-Key with createTask so a retried request for popnow/face-enhancer-video-v1/video-edit never runs or bills twice.
Common Video Face Enhancer API errors
| errorCode | What it usually means and how to fix it |
|---|---|
invalid_request | video_url is missing, or the clip is shorter than 3 seconds or longer than 5 minutes. Check the duration on the client before you call. |
invalid_asset | The file could not be fetched, is not an MP4, or the link is not publicly downloadable. Upload local files first and pass the returned reference. |
generation_failed | The restoration could not run on this file, often because the video stream is damaged. Re-encode the source to a standard MP4 and retry. |
timeout | A long clip ran past the processing limit. Split a film into scenes of a few minutes each, process them separately and join the results. |
Video Face Enhancer API questions
How much does the Video Face Enhancer API cost?
Video Face Enhancer costs $0.012 per second. 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.
What is the model name for Video Face Enhancer in the API?
Put popnow/face-enhancer-video-v1/video-edit for Video Face Enhancer in the model field of POST /jobs/createTask.
How long can the input clip be?
From 3 seconds to 5 minutes. A clip outside that range is refused before anything is charged.
Does the output keep the audio?
Yes. The original audio track comes back as it was, because only the picture is processed.
Are the faces stable from frame to frame?
The restoration works on the whole clip so a face stays steady. In our test a five-second podcast clip showed sharper eyes, teeth and hairlines in every frame, without flicker.
How is the price rounded?
Per second of input, rounded up to the next whole second, with a three-second minimum. A 4.2-second clip bills five seconds, which is $0.06.
What are the limits of the Video Face Enhancer API?
Longest input clip: 300 s. Requests outside these limits are rejected before anything is charged.
Can I try Video Face Enhancer without writing code?
Run Video Face Enhancer in the Playground with your API USD balance, without an API key. Each run appears in your developer history with its matching code.
All Video Face Enhancer models
Video Upscaler sharpens the whole clip and raises its resolution; Video Face Enhancer fixes faces at the same size.
