Nano Banana 2.1 is LIVE — Google's Latest | Try Now →

wavespeed-ai/face-enhancer/video

WaveSpeedAI Video Face Enhancer restores and sharpens faces throughout videos with stable, flicker-free results while preserving the original audio, making it suitable for face restoration, video enhancement, archival footage, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Upscale Video
Input
Enable Safety Checker

Idle

$0.05per run·~20 / $1

ExamplesView all

Related Models

README

Video Face Enhancer

Video Face Enhancer restores and sharpens faces throughout a video while preserving the original motion, framing, and audio. It tracks faces across frames, enhances details such as eyes, skin, hair, and teeth, and blends the restored regions back into the footage with improved temporal consistency.

The model is designed for low-resolution, compressed, soft, or AI-generated footage where facial detail needs to be recovered without changing the rest of the scene.

Why Choose This?

  • Temporally stable face enhancement
    Face landmarks are tracked and smoothed across frames to reduce shimmer and frame-to-frame instability.

  • Natural facial restoration
    Recover detail lost to blur, compression, or low resolution while preserving the subject's identity and expression.

  • Occlusion-aware processing
    Preserve foreground elements such as hands, hair strands, and glasses when they overlap the face.

  • Multi-face support
    Enhance up to 3 of the largest detected faces in each frame.

  • Original audio preserved
    Keep the source video's audio track in the final output.

  • Simple workflow
    Upload a video and generate the enhanced result without additional tuning parameters.

Parameters

ParameterRequiredDescription
videoYesInput video containing the faces to enhance. Supports upload or public URL. Maximum duration: 10 minutes.

How to Use

  1. Upload a video — Provide the source footage by upload or public URL.
  2. Submit — Run the face-enhancement process.
  3. Retrieve the result — Preview and download the enhanced video.

Pricing

Pricing is based on the input video duration.

The rate is $0.01 per billed second, equivalent to $0.05 per 5 seconds.

Input duration is rounded up to the next whole second, with a minimum billed duration of 3 seconds.

Video LengthBilled DurationCost
3s3s$0.03
15s15s$0.15
90s90s$0.90
300s300s$3.00
600s600s$6.00

The minimum charge is $0.03.

Best Use Cases

  • Old and compressed footage — Restore facial detail in archival, low-resolution, or heavily compressed videos.
  • AI-generated video — Improve soft or unstable-looking faces in generated footage.
  • Interviews and vlogs — Enhance facial clarity in talking-head and creator content.
  • Social media video — Improve face detail before publishing short-form or promotional content.
  • Portrait-focused footage — Restore facial detail while keeping the surrounding scene intact.

Pro Tips

  • Use footage where faces are reasonably visible for stronger restoration results.
  • The model prioritizes the largest detected faces when more than three faces appear in a frame.
  • Enhancement works best when the source still contains enough facial structure for the model to recover.
  • Very small, heavily obscured, or extremely blurred faces may show less improvement.
  • Review glasses, hair, hands, and other overlapping elements when the face is heavily occluded.
  • For AI-generated footage, use the enhancer after video generation when facial softness or detail loss is the main issue.

Notes

  • video is the only required parameter.
  • Maximum input duration is 10 minutes.
  • Up to 3 faces are enhanced per frame, prioritizing the largest detected faces.
  • The original audio track is preserved in the output.
  • The model is primarily designed for real human faces; illustrated or anime-style faces may show limited improvement.
  • Make sure you have permission to use the uploaded footage and likenesses.
Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Face Enhancer Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/face-enhancer/video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Face Enhancer Video below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/face-enhancer/video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/face-enhancer/video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/face-enhancer/video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Face Enhancer Video API — Frequently asked questions

What is the Face Enhancer Video API?

Face Enhancer Video is a WaveSpeedAI model for video upscaling, exposed as a REST API on WaveSpeedAI. WaveSpeedAI Video Face Enhancer restores and sharpens faces throughout videos with stable, flicker-free results while preserving the original audio, making it suitable for face restoration, video enhancement, archival footage, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Face Enhancer Video API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/face-enhancer-video.

How much does Face Enhancer Video cost per run?

Face Enhancer Video starts at $0.05 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Face Enhancer Video accept?

Key inputs: `video`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/face-enhancer-video.

How do I get started with the Face Enhancer Video API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Face Enhancer Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.

llms.txt — wavespeed-ai/face-enhancer/video for AI agents and LLMs