Face Enhancer Video API Documentation

Face Enhancer Video API Documentation

Playground

Restore and sharpen faces throughout any video with stable, flicker-free results and the original audio kept. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Video Face Enhancer restores and sharpens faces throughout a video. It tracks the faces in every frame, recovers natural detail in eyes, skin, hair and teeth, and blends them back smoothly — with stable, flicker-free results and the original audio kept.

Why It Looks Great

• Temporal stability: Face landmarks are smoothed across frames, so restored faces hold still instead of shimmering.
• Natural restoration: Recovers detail lost to blur, compression and low resolution while keeping identity and expression.
• Occlusion aware: Hands, hair strands and glasses in front of a face are preserved.
• Multi-face support: Up to three of the largest faces in each frame are enhanced.
• Original audio kept: The soundtrack is copied to the output unchanged.

Parameters

How to Use

1. Upload your video — drag and drop or paste a public URL.
2. Run — wait for processing.
3. Download — preview and save your enhanced video.

Pricing

> Billing duration: Input media duration is rounded up to whole seconds. The minimum billed duration is 3 seconds; shorter inputs are billed as 3 seconds.

Per-second billing with a 3-second minimum. Maximum video length: 10 minutes.

Billing Rules

• Minimum charge: 3 seconds ($0.03)
• Per-second rate: $0.01
• Billed duration: Video length in seconds (rounded up), with 3-second minimum
• Total cost: Billed duration × $0.01

Examples

Best Use Cases

• Old footage — Bring back facial detail in archival, compressed or low-resolution clips.
• AI-generated video — Sharpen soft or unstable faces in generated videos.
• Interviews & vlogs — Clearer faces for talking-head content.
• Social media — Crisper faces before posting.

Notes

• Up to 3 faces are enhanced per frame — the largest ones.
• Output resolution follows the input (capped at about 2000×1080 pixels) and frame rate is capped at 30 fps.
• Works best on real human faces; illustrated or anime faces may not improve.
• Ensure you have permission to use all uploaded videos 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