Architectural Video Presentations with Nano Banana and InfiniteTalk

Transform User-Generated Content into Immersive Architectural Presentation Videos with Nano Banana 2 and Infinite talk

 1import requests
 2import time
 3import json
 4
 5api_key = "YOUR_API_KEY"
 6url = "https://api.segmind.com/workflows/69b3a8f4e90fc09c1a796076-v1"
 7
 8data = {
 9    "Input_Image": [
10        "https://segmind-inference-inputs.s3.amazonaws.com/bd657628-3890-47ef-8d5c-02c760881a7a-df5b75bb-f352-4e04-9385-f74f503ce8f8.png",
11        "https://segmind-inference-inputs.s3.amazonaws.com/4f223367-ffcf-4edd-834e-9f9450783638-hf_20260219_114702_f0f039ae-91d0-46b5-b9f1-a5d21afecfc0.jpeg"
12    ],
13    "Voiceover_Script": "Step into a space designed for warmth, comfort, and quiet luxury, while natural stone walls and warm timber ceilings create a calming retreat. A central fire pit offers cozy gatherings even in the coldest weather, and plush seating invites you to relax, unwind, and fully experience the beauty outside."
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={'Authorization': f'Bearer {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        'Authorization': f'Bearer {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/69b3a8f4e90fc09c1a796076-v1

Parameters

Input_Imageoptional
array

Input Image

Default: ["https://segmind-inference-inputs.s3.amazonaws.com/bd657628-3890-47ef-8d5c-02c760881a7a-df5b75bb-f352-4e04-9385-f74f503ce8f8.png","https://segmind-inference-inputs.s3.amazonaws.com/4f223367-ffcf-4edd-834e-9f9450783638-hf_20260219_114702_f0f039ae-91d0-46b5-b9f1-a5d21afecfc0.jpeg"]
Voiceover_Scriptoptional
string

Voiceover Script

Default: "Step into a space designed for warmth, comfort, and quiet luxury, while natural stone walls and warm timber ceilings create a calming retreat. A central fire pit offers cozy gatherings even in the coldest weather, and plush seating invites you to relax, unwind, and fully experience the beauty outside."

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