Segmind Double Capsule Serverless API

Re-shoot footage you already have. Give Segmind Double Capsule a clip, a reference image and one sentence, and get the same take in a new location, light or season, or with a swapped prop. Seedance 2.5 edit keeps the performance and camera move. 10-bit, at your clip's exact length.

~363.32s
~$2.8976
 1import requests
 2import time
 3import json
 4
 5api_key = "YOUR_API_KEY"
 6url = "https://api.segmind.com/workflows/v2/6ae2ede23d93ec299cd95e70-v4"
 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    "smooth_retime_and_grain_match": true
14}
15
16def poll_for_result(poll_url):
17    """Poll the API until the generation is complete"""
18    while True:
19        response = requests.get(
20            poll_url,
21            headers={'x-api-key': api_key}
22        )
23        result = response.json()
24
25        if result['status'] == 'COMPLETED':
26            # Parse the output (it's a JSON string)
27            outputs = json.loads(result['output'])
28            return outputs
29        elif result['status'] == 'FAILED':
30            raise Exception(result.get('error', 'Generation failed'))
31
32        # Wait 7 seconds before polling again
33        time.sleep(7)
34
35# Make the initial request
36response = requests.post(
37    url,
38    json=data,
39    headers={
40        'x-api-key': api_key,
41        'Content-Type': 'application/json'
42    }
43)
44
45if response.status_code == 200:
46    result = response.json()
47    print('Request queued:', result)
48
49    # Start polling for results
50    outputs = poll_for_result(result['poll_url'])
51    print('Generation complete:', outputs)
52else:
53    print(f"Error: {response.status_code}")
54    print(response.text)

API Endpoint

POSThttps://api.segmind.com/workflows/v2/6ae2ede23d93ec299cd95e70-v4

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"
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