Trellis - 3D Image Generator
Generate high-quality 3D models from 2D images using Trellis AI model. Trellis creates detailed 3D GLB files that can be used in various 3D applications and viewers.
Endpoint
Request Body
The request must include the following parameters:
Parameter | Type | Required | Description |
---|---|---|---|
type | string | Yes | Feature type identifier. Must be IMAGE_3D_GENERATOR |
model | string | Yes | AI model identifier. Must be Qubico/trellis |
promptObject | object | Yes | Feature-specific parameters |
Prompt Object Parameters
Parameter | Type | Required | Description |
---|---|---|---|
imageUrl | string | Yes | Path to the 2D image to convert into a 3D model |
Example Request
- JavaScript
- cURL
- Python
fetch('https://api.1min.ai/api/features', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'API-KEY': 'YOUR_API_KEY'
},
body: JSON.stringify({
type: 'IMAGE_3D_GENERATOR',
model: 'Qubico/trellis',
promptObject: {
imageUrl: 'development/images/2025_02_18_17_07_32_777_object.jpg'
}
})
})
curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "IMAGE_3D_GENERATOR",
"model": "Qubico/trellis",
"promptObject": {
"imageUrl": "development/images/2025_02_18_17_07_32_777_object.jpg"
}
}'
import requests
url = "https://api.1min.ai/api/features"
headers = {
"Content-Type": "application/json",
"API-KEY": "YOUR_API_KEY"
}
data = {
"type": "IMAGE_3D_GENERATOR",
"model": "Qubico/trellis",
"promptObject": {
"imageUrl": "development/images/2025_02_18_17_07_32_777_object.jpg"
}
}
response = requests.post(url, headers=headers, json=data)
Responses
Success Response (200)
Successful response contains the generated 3D model in GLB format.
{
"success": true,
"data": {
"resultObject": [
"path/to/generated_model.glb"
]
}
}
Features
Key Capabilities
- High-Quality 3D Generation: Creates detailed 3D models from single 2D images
- GLB Output Format: Generates industry-standard GLB files compatible with most 3D viewers and applications
- Automatic Depth Inference: Intelligently infers 3D depth and structure from 2D input
- Texture Preservation: Maintains color and texture information from the original image
Best Practices
- Image Quality: Use high-resolution images with clear subjects for best results
- Subject Isolation: Images with well-defined subjects against simple backgrounds work best
- Object Types: Works well with objects, products, furniture, and simple scenes
- Lighting: Images with even lighting produce more accurate 3D models
Output Format
The generated 3D model is provided in GLB (GL Transmission Format Binary) format, which:
- Contains geometry, materials, and textures in a single file
- Is widely supported by 3D software and web viewers
- Can be directly used in AR/VR applications
- Is optimized for web delivery and real-time rendering
Use Cases
- E-commerce: Create 3D product views from product photos
- Gaming: Generate 3D assets from concept art
- AR/VR: Create 3D content for immersive experiences
- Digital Marketing: Enhance presentations with 3D visuals
- 3D Printing: Generate printable 3D models from images
Notes
- Processing time varies based on image complexity
- The model works best with objects that have clear boundaries
- Generated models may require minor adjustments for specific use cases
- The GLB file can be viewed in any 3D model viewer or imported into 3D software