Face Enhancer Video API Documentation

Face Enhancer Video API Documentation

Playground

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.

Features

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

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.

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.

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"
}
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 "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters