Image Face Swap API Documentation

Image Face Swap API Documentation

Playground

Free swap faces in any photo instantly — realistic blending, no watermark, no sign up. Upload a base image and reference face to get started now.

Features

Face Swap is an advanced AI-powered face replacement model that enables realistic, seamless, and watermark-free face swaps in static images. By combining powerful face recognition, alignment, and blending algorithms, it ensures lifelike results while preserving lighting, pose, and expression fidelity.

⚙️ Why it looks so cool

• Instant Face Swapping Upload a base image and a reference face — the model replaces the original face with the target identity while maintaining natural contours and lighting.

• Realistic Blending Automatically adapts skin tone, lighting direction, and expression for ultra-smooth integration.

• Expression & Pose Preservation The source image’s emotion, head tilt, and gaze direction are retained for believable results.

• Watermark-Free Results Every generation is clean, production-ready, and suitable for both fun edits and professional use.

🧠 How to use

• Input:

• image → The base photo to edit

• face_image → The reference face to swap in

• target_index → (optional) Which face to swap when multiple faces exist; 0 = largest face. Default: 0

• target_gender → (optional) Only swap faces matching this gender: all, male, or female. Default: all

• Output: JPEG / PNG / WEBP image with replaced face

• AI Engine: WaveSpeedAI Face Identity Alignment & Lighting Consistency Module

💰 Pricing

💡 Best Use Cases

• Social Media & Entertainment — Fun, shareable, and creative swaps in portraits and group photos.
• Film & Advertising — Quick mockups for casting, storyboarding, and concept design.
• Photography & Visual Design — Replace faces for privacy, retouching, or creative effects.
• Virtual Production — Generate realistic composites for narrative or promotional visuals.

📝 Notes

• For best results, use clear, front-facing portraits with consistent lighting between both faces.
• Avoid overly complex or low-resolution images — clarity improves blending accuracy.
• Ensure you have permission to use all uploaded images and likenesses.
• If you are working with anime or illustrated characters, the output quality may be significantly lower due to visual style differences.

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'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "face_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "target_index": 0,
  "target_gender": "all",
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/image-face-swap" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters