No description available.
Run the model to see results
Run the model to see JSON response
POST https://lumozai.com/api/v4/run
Use this endpoint to run the model with your parameters. Authentication is required using your API key.
<?php // API endpoint URL $apiUrl = 'https://lumozai.com/api/v4/run'; // Your API key $apiKey = 'YOUR_API_KEY'; // Model parameters $params = [ 'model_id' => chat-gpt-ghibli, 'prompt' => 'Create a whimsical Studio Ghibli-style illustration of a serene forest village at sunrise. The scene features quaint, moss-covered cottages with curved roofs nestled among ancient, towering trees. Gentle rays of golden sunlight filter through the misty air, illuminating a winding cobblestone path. Friendly forest spirits, resembling small, fluffy creatures with glowing eyes, peek out from behind ferns and tree trunks. A young girl in a flowing dress stands on a wooden bridge over a sparkling stream, holding a lantern as she gazes at the awakening village. The color palette is soft and warm, with lush greens, earthy browns, and hints of pastel pinks and oranges in the sky. Capture the magical, nostalgic essence of a Ghibli film with intricate details and a sense of wonder.', 'aspect_ratio' => '1:1', 'prompt_strength' => 0.8, 'num_inference_steps' => 28, 'guidance' => 3, 'seed' => '', 'output_format' => 'webp', 'output_quality' => 80, 'lora_scale' => 1, 'megapixels' => '1', ]; // 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);
Parameter | Type | Required | Description |
---|---|---|---|
model_id | string | Required | The ID of the model to run (chat-gpt-ghibli) |
api_key | string | Required | Your API key for authentication (sent via Bearer token in the Authorization header) |
prompt | string | Required | Describe what you want to generate |
aspect_ratio | string | Required | Aspect ratio for the generated image |
prompt_strength | number | Optional | Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image |
num_inference_steps | number | Optional | Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster. |
guidance | number | Optional | Guidance for generated image |
seed | number | Optional | Random seed. Set for reproducible generation |
output_format | string | Optional | Format of the output images |
output_quality | number | Optional | Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs |
lora_scale | number | Optional | Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value. |
megapixels | string | Optional | Approximate number of megapixels for generated image |
{ "success": true, "data": { "output": "https://lumozai.com/storage/outputs/image_12345.jpg" } }
Cost Per Generation is a pricing model where you’re charged based on each individual output the model generates. Instead of billing for compute time, you pay a fixed cost for every generation request, regardless of how long it takes. This makes costs predictable since each generated result incurs its own set rate.
Note: Pricing is subject to change. For bulk usage or custom packages, please contact us.