Akool Image Face Swap
Playground
Try it on WaveSpeedAI!Akool Image Face Swap swaps faces in photos using a source and target image, including multi-face replacement for group photos. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Akool Image Face Swap is a powerful AI-powered face swapping model that seamlessly replaces faces in images with remarkable precision and realism. Swap single or multiple faces in one image while preserving natural lighting, skin tone, and facial expressions.
Why It Stands Out
- Multi-face swapping: Swap multiple faces in a single image simultaneously.
- High-quality blending: Seamlessly integrates swapped faces with natural lighting and skin tone matching.
- Face enhancement: Optional post-swap face quality enhancement for sharper, cleaner results.
- Flexible input: Upload multiple source and target face images for precise control.
- One-click operation: Simple workflow — upload images and get results instantly.
Parameters
| Parameter | Required | Description |
|---|---|---|
| image | Yes | The main image where faces will be swapped. |
| source_image | Yes | Face(s) to use as replacement (can add multiple). |
| target_image | Yes | Face(s) in the main image to be replaced (can add multiple). |
| face_enhance | No | Enhance face quality after swapping (default: enabled). |
| enable_base64_output | No | Return base64 string instead of URL (API only). |
How to Use
- Upload the main image — the image where you want to swap faces.
- Add source image(s) — upload the face(s) you want to use as replacements.
- Add target image(s) — upload reference images of the face(s) to be replaced in the main image.
- Enable face enhance (recommended) — improves output quality.
- Click Run and wait for processing.
- Preview and download the result.
Best Use Cases
- Creative Projects — Create fun, artistic face swaps for personal projects.
- Content Creation — Generate engaging content for social media and entertainment.
- Marketing & Advertising — Visualize models or personas in different scenarios.
- Film & Video Production — Create concept images for pre-visualization.
- E-commerce — Show products on different face types for diverse representation.
Pricing
| Output | Price |
|---|---|
| Per image | $0.16 |
Pro Tips for Best Quality
- Use high-resolution, well-lit face images for both source and target.
- Ensure faces are clearly visible and not obscured by accessories or hair.
- For best matching, use source faces with similar angles to the target faces.
- Keep face_enhance enabled for sharper, more natural-looking results.
- When swapping multiple faces, match source and target images in the same order.
Notes
- Ensure uploaded image URLs are publicly accessible.
- Processing time varies based on the number of faces and current queue load.
- Please use responsibly and ensure your content complies with usage guidelines.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"source_image": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"target_image": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"face_enhance": false
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/akool/image-face-swap" \
-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 "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(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' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
esac
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| image | string | Yes | - | Image URL to be swapped | |
| source_image | array<string> | Yes | - | 1 ~ 5 items | Source face image URL to be swapped into the video |
| target_image | array<string> | Yes | - | 1 ~ 5 items | Target face image URL that will be replaced in the video |
| face_enhance | boolean | No | false | - | Whether to enhance face quality after swapping |
| enable_base64_output | boolean | No | false | - | If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |