Faceswap V3 Serverless API

Face Swap V3 is a cutting-edge tool that empowers you to seamlessly swap faces in images. With customizable features and advanced technology, you can achieve professional-quality results.

~4.32s
PlaygroundAPI
Pricing
POST /v2/faceswap-v3 · submit + poll
 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3import segmind
 4
 5# Async (v2): submit to the queue and block until COMPLETED.
 6# run() returns the final result dict (600s deadline, 1.0s poll by default).
 7result = segmind.run(
 8    "faceswap-v3",
 9    source_img="https://segmind-sd-models.s3.amazonaws.com/display_images/faceswapv2_target.jpg",
10    target_img="https://segmind-sd-models.s3.us-east-1.amazonaws.com/elon.jpg",
11    input_faces_index="0",
12    source_faces_index="0",
13    face_restore="codeformer-v0.1.0.pth",
14    interpolation="Bilinear",
15    detection_face_order="large-small",
16    facedetection="retinaface_resnet50",
17    detect_gender_input="no",
18    detect_gender_source="no",
19    face_restore_weight=0.75,
20    image_format="jpeg",
21    image_quality=95,
22    base64=False,
23)
24print(result["status"])                      # COMPLETED
25print(result.get("output"))                  # model output (e.g. media URL)
26print(result["metrics"]["inference_time"])   # server compute seconds
27
28# --- Or submit + poll manually (track request_id, control the cadence) ---
29from segmind import SegmindClient, InferenceFailed, InferenceTimeout
30
31client = SegmindClient()                      # reads SEGMIND_API_KEY
32payload = {
33    "source_img": "https://segmind-sd-models.s3.amazonaws.com/display_images/faceswapv2_target.jpg",
34    "target_img": "https://segmind-sd-models.s3.us-east-1.amazonaws.com/elon.jpg",
35    "input_faces_index": "0",
36    "source_faces_index": "0",
37    "face_restore": "codeformer-v0.1.0.pth",
38    "interpolation": "Bilinear",
39    "detection_face_order": "large-small",
40    "facedetection": "retinaface_resnet50",
41    "detect_gender_input": "no",
42    "detect_gender_source": "no",
43    "face_restore_weight": 0.75,
44    "image_format": "jpeg",
45    "image_quality": 95,
46    "base64": False,
47}
48job = client.submit_async("faceswap-v3", **payload)
49print(job.request_id)                         # available immediately
50try:
51    result = job.wait(timeout=600, interval=1.0)
52except InferenceTimeout as e:
53    print("still running:", e.request_id)
54except InferenceFailed as e:
55    print("failed:", e.detail)

API Endpoint

POSThttps://api.segmind.com/v1/faceswap-v3

Parameters

source_imgrequired
string (uri)

Your face goes here. A closeup shot would be ideal.(image url)

target_imgrequired
string (uri)

The face you want to swap with (image url).

base64optional
boolean

Base64 encoding of the output image.

Default: false
detect_gender_inputoptional
string

Detect the gender of the target face

Default: "no"
Allowed values :
"no""female""male"
detect_gender_sourceoptional
string

Detect the gender of the input face

Default: "no"
Allowed values :
"no""female""male"
detection_face_orderoptional
string

The order in which faces are detected.

Default: "large-small"
Allowed values :
"large-small""small-large""top-bottom""bottom-top""left-right""right-left"
face_restoreoptional
string

which face restore model to use

Default: "codeformer-v0.1.0.pth"
Allowed values :
"codeformer-v0.1.0.pth""GFPGANv1.4.pth""GFPGANv1.3.pth"
face_restore_weightoptional
number

Face Restore Weight

Default: 0.75Range: 0 - 1
facedetectionoptional
string

The model used to detect the face

Default: "retinaface_resnet50"
Allowed values :
"retinaface_resnet50""retinaface_mobile0.25""YOLOv5l""YOLOv5n"
image_formatoptional
string

Output image format

Default: "jpeg"
Allowed values :
"jpeg""png""webp"
image_qualityoptional
integer

Image quality setting for output

Default: 95Range: 10 - 100
input_faces_indexoptional
string

Index of the input faces: By default the model detects faces in images from 'large' to 'small'.Index of the first detected face is 0. Multiple faces can be selected using a comma (,)

Default: "0"
interpolationoptional
string

Face restore interpolation method

Default: "Bilinear"
Allowed values :
"Nearest""Bilinear""Bicubic""Lanczos"
source_faces_indexoptional
string

Index of the source faces: By default the model detects faces in images from 'large' to 'small'.Index of the first detected face is 0. Multiple faces can be selected using a comma (,)

Default: "0"

Response Type

Returns: Image

Asynchronous requests (v2)

Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.

  1. 1
    POST /v2/faceswap-v3

    Submit — returns request_id, status_url, response_url

  2. 2
    GET /v2/requests/{id}/status

    Poll — until COMPLETED or FAILED

  3. 3
    GET /v2/requests/{id}

    Result — final response body

Status states

QUEUED— Accepted, waiting for a worker
PROCESSING— Running on a worker
COMPLETED— Done — result body is ready
FAILED— Errored (incl. content/RAI blocks)
  • A FAILED request is served as HTTP 422 — the body still carries the error detail.
  • An unknown or expired request_id returns HTTP 404.
  • Results are retained for 1 hour, then expire.
  • Content / RAI blocks surface as FAILED, not a separate state.
  • Track completion by polling the status endpoint.

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid parameters or request format

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out