Segmind Double Capsule Plate Composite Serverless API

Plate-composite AI reshoots: the real actor from your footage is matted, relit and composited over a Seedance 2.5 edit of the new location, light or season. For film, TV and ad studios: up to 1080p, 10-bit HEVC at your clip's exact length and frame rate, plus the actor matte pass.

~450.83s
~$3.4133
 1import requests
 2import time
 3import json
 4
 5api_key = "YOUR_API_KEY"
 6url = "https://api.segmind.com/workflows/v2/6ae35f9c79d78eae84bc5b90-v1"
 7
 8data = {
 9    "source_video": "https://images.segmind.com/public/01ee3fbafb4860ea4c64322c0e096e81.mp4",
10    "reference_image": "https://images.segmind.com/public/baba54a04431418c3865228d4c6377c6.jpeg",
11    "change": "Change the setting and the light to the back room of the 1920s jazz club in @Image 1: blue haze, warm brass table lamps; keep his cigarette smoke",
12    "keep": "the man in a white shirt, tie and suspenders",
13    "resolution": "1080p",
14    "smooth_retime_and_grain_match": true
15}
16
17def poll_for_result(poll_url):
18    """Poll the API until the generation is complete"""
19    while True:
20        response = requests.get(
21            poll_url,
22            headers={'x-api-key': api_key}
23        )
24        result = response.json()
25
26        if result['status'] == 'COMPLETED':
27            # Parse the output (it's a JSON string)
28            outputs = json.loads(result['output'])
29            return outputs
30        elif result['status'] == 'FAILED':
31            raise Exception(result.get('error', 'Generation failed'))
32
33        # Wait 7 seconds before polling again
34        time.sleep(7)
35
36# Make the initial request
37response = requests.post(
38    url,
39    json=data,
40    headers={
41        'x-api-key': api_key,
42        'Content-Type': 'application/json'
43    }
44)
45
46if response.status_code == 200:
47    result = response.json()
48    print('Request queued:', result)
49
50    # Start polling for results
51    outputs = poll_for_result(result['poll_url'])
52    print('Generation complete:', outputs)
53else:
54    print(f"Error: {response.status_code}")
55    print(response.text)

API Endpoint

POSThttps://api.segmind.com/workflows/v2/6ae35f9c79d78eae84bc5b90-v1

Parameters

source_videooptional
string (uri)

Source Video

Default: "https://images.segmind.com/public/01ee3fbafb4860ea4c64322c0e096e81.mp4"
reference_imageoptional
string (uri)

Reference Image

Default: "https://images.segmind.com/public/baba54a04431418c3865228d4c6377c6.jpeg"
changeoptional
string

Change

Default: "Change the setting and the light to the back room of the 1920s jazz club in @Image 1: blue haze, warm brass table lamps; keep his cigarette smoke"
keepoptional
string

Keep

Default: "the man in a white shirt, tie and suspenders"
resolutionoptional
string

Resolution

Default: "1080p"
smooth_retime_and_grain_matchoptional
boolean

Smooth retime + grain match

Default: true

Response Format

Returns: Polling-based asynchronous response

Initial request returns a poll_url. Poll every 7 seconds until status is COMPLETED.

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

Workflow 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