Getting Great Results from Training
Follow these best practices to ensure your custom models produce high-quality outputs.
Image Quality Matters
Resolution
Minimum: 512 x 512 pixels
Recommended: 1024 x 1024 or higher
Higher resolution = more detail captured
Focus & Clarity
Sharp, well-focused images
Avoid motion blur
Good exposure (not too dark or bright)
File Format
JPG or PNG recommended
Avoid heavily compressed files
No watermarks or overlays
How Many Images?
You only need a minimum of 1 image to train a model. We recommend uploading several for better results.
Which images matter most?
Style models: The first 5 images have the highest impact
Person, Object & Scene models: The first 3 images have the highest impact
Image order matters — if you're not satisfied with results, try reordering your training images.
Variety in Training Sets
For Person Models:
Different angles: front, side, 3/4
Various expressions
Indoor and outdoor
Different outfits
For Style Models:
Different subjects
Same consistent style
Various compositions
For Object Models:
Multiple angles
Different scales
Various lighting setups
For Scene Models:
Wide and close views
Different perspectives
Various times of day
Common Mistakes to Avoid
Low variety: Same pose/angle in every image
Inconsistent subjects: Mixing different people/objects
Poor quality: Blurry, dark, or compressed images
Wrong model type: Choosing style when you mean object
Busy backgrounds: Distracting elements in training images
Checking Training Results
After training (takes around 20 seconds):
Generate test images with different prompts
Try various styles and settings
Check for consistency in outputs
If unsatisfied, try reordering your training images or adding new ones
When to Retrain
Results don't capture the subject accurately
Output is inconsistent
Model doesn't respond well to prompts
You have better training images available