Training Person Models

Training a Person Model

Person models learn to recognize and recreate a specific individual. Once trained, you can generate that person in any style, setting, or scenario.

Image Requirements

Number of Images: 10-20 photos

Image Guidelines:

• Clear face visibility in all photos

• Variety of expressions and angles

• Different lighting conditions

• Various backgrounds (not all the same)

• High resolution (at least 512x512)

• Only the person you're training (no group photos)

What to Include

Good training images:

• Portrait shots (front, profile, 3/4 view)

• Different expressions (smiling, neutral, serious)

• Indoor and outdoor lighting

• Casual and formal appearances

• Full face visibility

Avoid:

• Heavy makeup or costumes

• Sunglasses or masks covering face

• Extreme angles or blur

• Photos with multiple people

• Low resolution or heavily filtered images

Training Process

1. Navigate to Models > Create New Model

2. Select Person as the model type

3. Upload your training images

4. Enter a name for your model

5. Click Start Training

6. Wait approximately 15-30 minutes

Credit Cost

Training a Person model costs 400 credits.

Using Your Person Model

After training, use your model by including its trigger word in prompts:

> "[trigger word] as a medieval knight in armor, dramatic lighting" > "Professional headshot of [trigger word] in a modern office" > "[trigger word] on a beach at sunset, cinematic style"

Tips for Better Results

1. Be specific in prompts: Describe the scene, style, and mood

2. Match the style: Your trained person can appear in any style

3. Experiment: Try different scenarios to see what works best

4. Iterate: Refine prompts based on results