Script to Background Design - Microdrama Serverless API

Transform Scripts into Stunning Backgrounds for Microdramas using Claude 4.5 and GPT Image.

 1import requests
 2import time
 3import json
 4
 5api_key = "YOUR_API_KEY"
 6url = "https://api.segmind.com/workflows/v2/6a8008be4fa8b6a09434f886-v1"
 7
 8data = {
 9    "input_prompt": "Title: \"The Debt\"\n\n(A dimly lit alley. JI-HOON, a delivery worker, blocks the path of MIN-JAE, a loan shark in an expensive coat.)\n\nMIN-JAE: (smirking) Move aside, kid. Your father's debt isn't your problem.\n\nJI-HOON: (standing firm) It became mine the day he died protecting this street from men like you.\n\nMIN-JAE: (stepping closer) Sentiment doesn't pay bills.\n\nJI-HOON: (pulls out a worn ledger) Neither does fear — not anymore. Everyone you've cheated signed this. Tomorrow, they go to the police together.\n\nMIN-JAE: (freezes, smile fading) You're bluffing.\n\nJI-HOON: (quiet, steady) Test me.\n\n(MIN-JAE stares — then turns and walks away into the dark. JI-HOON exhales, clutching the ledger to his chest.)\n\n[END]"
10}
11
12def poll_for_result(poll_url):
13    """Poll the API until the generation is complete"""
14    while True:
15        response = requests.get(
16            poll_url,
17            headers={'x-api-key': api_key}
18        )
19        result = response.json()
20
21        if result['status'] == 'COMPLETED':
22            # Parse the output (it's a JSON string)
23            outputs = json.loads(result['output'])
24            return outputs
25        elif result['status'] == 'FAILED':
26            raise Exception(result.get('error', 'Generation failed'))
27
28        # Wait 7 seconds before polling again
29        time.sleep(7)
30
31# Make the initial request
32response = requests.post(
33    url,
34    json=data,
35    headers={
36        'x-api-key': api_key,
37        'Content-Type': 'application/json'
38    }
39)
40
41if response.status_code == 200:
42    result = response.json()
43    print('Request queued:', result)
44
45    # Start polling for results
46    outputs = poll_for_result(result['poll_url'])
47    print('Generation complete:', outputs)
48else:
49    print(f"Error: {response.status_code}")
50    print(response.text)

API Endpoint

POSThttps://api.segmind.com/workflows/v2/6a8008be4fa8b6a09434f886-v1

Parameters

input_promptoptional
string

Input Prompt

Default: "Title: \"The Debt\"\n\n(A dimly lit alley. JI-HOON, a delivery worker, blocks the path of MIN-JAE, a loan shark in an expensive coat.)\n\nMIN-JAE: (smirking) Move aside, kid. Your father's debt isn't your problem.\n\nJI-HOON: (standing firm) It became mine the day he died protecting this street from men like you.\n\nMIN-JAE: (stepping closer) Sentiment doesn't pay bills.\n\nJI-HOON: (pulls out a worn ledger) Neither does fear — not anymore. Everyone you've cheated signed this. Tomorrow, they go to the police together.\n\nMIN-JAE: (freezes, smile fading) You're bluffing.\n\nJI-HOON: (quiet, steady) Test me.\n\n(MIN-JAE stares — then turns and walks away into the dark. JI-HOON exhales, clutching the ledger to his chest.)\n\n[END]"

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