This example demonstrates how to select between different AI models for
background removal. Each model has different characteristics in terms of
speed, accuracy, and use cases.
⚠️ Data Usage Notice: First-time usage will download the
AI model (~200-300MB). Subsequent uses will load from cache. Please ensure
you have a stable internet connection and sufficient data allowance.
Available Models:
U2Net: General purpose, balanced speed and accuracy
U2NetP: Lightweight version, fastest processing
U2Net Human Segmentation: Optimized for
people/portraits
U2Net Cloth Segmentation: Specialized for clothing
items
Silueta: Alternative model with different
characteristics
ISNet General Use: High accuracy for general images
ISNet Anime: Optimized for anime/manga style images
U2Net (General Purpose): Balanced model suitable for
most images. Good accuracy with reasonable processing time.
