AI-Powered Virtual Try-On Video Creation with Kling 2.1

Create hyper-realistic virtual try-on videos from static images using Kling 2.1 AI.

~$0.9421
 1import requests
 2import time
 3import json
 4
 5api_key = "YOUR_API_KEY"
 6url = "https://api.segmind.com/workflows/68f1edea2431ac976656e99b-v1"
 7
 8data = {
 9    "Image_Input": "https://segmind-inference-inputs.s3.amazonaws.com/3c2f4963-c4cb-46f5-9585-31e6aed17ec1-be695278-fb85-4fd2-8be0-7efa0ccb4933.jpg",
10    "Input_Prompt": "A cinematic, hyper-realistic scene featuring a male model seated at the center of the frame on a minimalist vintage office chair. He wears a sleek black leather jacket, oversized leather pants, and modern sneakers. The camera is completely static as the model slowly rotates in place, maintaining a relaxed yet confident posture with his arms resting naturally by his sides. The lighting is soft and directional, creating subtle highlights on the glossy leather surfaces while casting smooth, dramatic shadows that define the folds and contours of the outfit. The background is pure white and uncluttered, emphasizing the silhouette and sharp lines of his look. The scene feels minimal, elegant, and hypnotic — the slow, deliberate rotation drawing focus to the play of light, texture, and form in a modern, fashion-editorial atmosphere."
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={'Authorization': f'Bearer {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        'Authorization': f'Bearer {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/68f1edea2431ac976656e99b-v1

Parameters

Image_Inputoptional
string (uri)

Image Input

Default: "https://segmind-inference-inputs.s3.amazonaws.com/3c2f4963-c4cb-46f5-9585-31e6aed17ec1-be695278-fb85-4fd2-8be0-7efa0ccb4933.jpg"
Input_Promptoptional
string

Input Prompt

Default: "A cinematic, hyper-realistic scene featuring a male model seated at the center of the frame on a minimalist vintage office chair. He wears a sleek black leather jacket, oversized leather pants, and modern sneakers. The camera is completely static as the model slowly rotates in place, maintaining a relaxed yet confident posture with his arms resting naturally by his sides. The lighting is soft and directional, creating subtle highlights on the glossy leather surfaces while casting smooth, dramatic shadows that define the folds and contours of the outfit. The background is pure white and uncluttered, emphasizing the silhouette and sharp lines of his look. The scene feels minimal, elegant, and hypnotic — the slow, deliberate rotation drawing focus to the play of light, texture, and form in a modern, fashion-editorial atmosphere."

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