Krea 3
Krea 3 is an advanced unified image generation and editing model. Edit photos using natural language instructions, blend up to 8 reference images, or generate pristine artwork at 1K or 2K resolutions with adaptive reasoning modes.
API endpoint
POST
https://lumozai.com/api/v4/run
Use this endpoint to run the model with your parameters. Authentication is required using your API key.
Sample code (PHP cURL)
PHP (cURL)
<?php
// API endpoint URL
$apiUrl = 'https://lumozai.com/api/v4/run';
// Your API key
$apiKey = 'YOUR_API_KEY';
// Model parameters
$params = [
'model_id' => 'krea-3',
'prompt' => '',
'images[]' => 'https://example.com/image.jpg', // Example image URL
'aspect_ratio' => 'auto',
'resolution' => '2k',
'thinking_mode' => 'fast',
'regional_edit' => 'false',
'negative_prompt' => '',
'seed' => '',
];
// Initialize cURL session
$curl = curl_init();
// Set cURL options
curl_setopt_array($curl, [
CURLOPT_URL => $apiUrl,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_POST => true,
CURLOPT_POSTFIELDS => $params,
CURLOPT_HTTPHEADER => [
'Accept: application/json',
'Authorization: Bearer ' . $apiKey
]
]);
// Execute the request
$response = curl_exec($curl);
$httpCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
// Check for errors
if (curl_errno($curl)) {
echo 'cURL Error: ' . curl_error($curl);
} else {
// Process the response
$result = json_decode($response, true);
if ($httpCode == 200 && isset($result['success']) && $result['success']) {
// Handle successful response
echo 'Model output: ';
print_r($result['data']['output']);
} else {
// Handle error response
echo 'Error: ' . ($result['message'] ?? 'Unknown error');
}
}
// Close cURL session
curl_close($curl);
Request parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
model_id |
string | Required | The ID of the model to run (krea-3) |
api_key |
string | Required | Your API key for authentication (sent via Bearer token in the Authorization header) |
prompt |
string | Required | Instruction describing the image to generate, or the edit to make. For edits, specify what should change and what should stay the same. |
images |
array | Optional | Up to 8 input reference images to edit, restyle, or combine. Leave empty for text-to-image generation. |
aspect_ratio |
string | Optional | Aspect ratio of the generated image. "auto" picks the optimal framing from your prompt or input images. |
resolution |
string | Optional | Output image resolution tier. |
thinking_mode |
string | Optional | How much reasoning and planning happens before generation. "fast" is rapid and works for most requests. "high" plans complex multi-step edits more thoroughly. |
regional_edit |
string | Optional | Change only specific parts of the image and keep the rest untouched (requires at least one reference image). |
negative_prompt |
string | Optional | Specific visual artifacts, concepts, or elements to avoid in the output. |
seed |
array | Optional | Specific random seed integer. |
Response format
JSON
{
"success": true,
"data": {
"output": "https://lumozai.com/storage/outputs/example.png"
}
}
تسعير النموذج
ادفع فقط مقابل ما تشغّله. تُخصم التكلفة مباشرة من رصيدك دون أي التزامات متكررة.
Rate per generation
$
0.06
/ generation
$60.00 per 1,000 generations
حاسبة التكلفة
1,000 generations
الإجمالي التقديري
$60.00
استرداد تلقائي فوري عند فشل أي عملية • الرصيد صالح لمدة عام