Change the Background of a Video Serverless API

Change the background of a video without a green screen. Describe the new place; the face, gestures and lip sync stay. Made with Gemini Omni 1.2 Flash.

~1m 32s
~$0.6723
 1import requests
 2import time
 3import json
 4
 5api_key = "YOUR_API_KEY"
 6url = "https://api.segmind.com/workflows/v2/6aecd2e42f75a5a513e8da40-v1"
 7
 8data = {
 9    "clip": "https://images.segmind.com/public/284a3d8dd2bec2bcb460fd7c3afb16c3.mp4",
10    "new_place": "A bright glass-walled meeting room high above a city skyline at golden hour"
11}
12
13def poll_for_result(poll_url):
14    """Poll the API until the generation is complete"""
15    while True:
16        response = requests.get(
17            poll_url,
18            headers={'x-api-key': api_key}
19        )
20        result = response.json()
21
22        if result['status'] == 'COMPLETED':
23            # Parse the output (it's a JSON string)
24            outputs = json.loads(result['output'])
25            return outputs
26        elif result['status'] == 'FAILED':
27            raise Exception(result.get('error', 'Generation failed'))
28
29        # Wait 7 seconds before polling again
30        time.sleep(7)
31
32# Make the initial request
33response = requests.post(
34    url,
35    json=data,
36    headers={
37        'x-api-key': api_key,
38        'Content-Type': 'application/json'
39    }
40)
41
42if response.status_code == 200:
43    result = response.json()
44    print('Request queued:', result)
45
46    # Start polling for results
47    outputs = poll_for_result(result['poll_url'])
48    print('Generation complete:', outputs)
49else:
50    print(f"Error: {response.status_code}")
51    print(response.text)

API Endpoint

POSThttps://api.segmind.com/workflows/v2/6aecd2e42f75a5a513e8da40-v1

Parameters

clipoptional
string (uri)

Clip

Default: "https://images.segmind.com/public/284a3d8dd2bec2bcb460fd7c3afb16c3.mp4"
new_placeoptional
string

New Place

Default: "A bright glass-walled meeting room high above a city skyline at golden hour"

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