hidream-l1
HiDream-I1 is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.
See It In Action
Explore real outputs from this model. Click any example to instantly load its parameters and view results.
#1
#2
#3
#4
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
// API endpoint URL
$apiUrl = 'https://lumozai.com/api/v4/run';
// Your API key
$apiKey = 'YOUR_API_KEY';
// Model parameters
$params = [
'model_id' => 'hidream-l1',
'seed' => '10',
'prompt' => 'a purple cheetah holding a sign that says ',
'speed_mode' => 'Extra Juiced 🚀 (even more speed)',
'resolution' => '1024 Ă— 1024 (Square)',
'output_format' => 'png',
'output_quality' => '80',
'negative_prompt' => '',
];
// 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 (hidream-l1) |
| api_key | string | Required | Your API key for authentication (sent via Bearer token in the Authorization header) |
| seed | array | Optional | Random seed for reproducibility |
| prompt | string | Required | Describe what you want to generate |
| speed_mode | string | Required | Select the generation speed |
| resolution | string | Required | Select the Resolution |
| output_format | string | Required | Select the output format |
| output_quality | number | Required | Set the quality of the generated image |
| negative_prompt | string | Optional |
Response Format
{
"success": true,
"data": {
"output": "https://lumozai.com/storage/outputs/image_12345.jpg"
}
}
Predictable, Output-Based Pricing
Zero server rental costs, zero cold-start tax, and no monthly lock-in. You only pay for successful inference calls.
Billed in real-time from your prepaid balance per second. No minimum commitments.
Zero Error Billing
100% automated refund guarantee. If an API request encounters a failure or network timeout, credits are refunded instantly.
Serverless Speed
High-concurrency global inference cluster with ultra-low latency, zero queue bottlenecks, and automated horizontal scaling.
Commercial Ownership
Full commercial ownership for all generated media, assets, and outputs with no attribution or royalties required.
Unified API & Web UI
Single billing balance across both developer cURL / REST API keys and the interactive web studio.