-
Notifications
You must be signed in to change notification settings - Fork 2
GPU Support
Aas1kk edited this page May 20, 2025
·
1 revision
GPU Speed Boost utilizes your computer's graphics card to dramatically increase processing speed. This feature is especially useful when processing large images or batches of photos.
- CUDA acceleration
- Batch processing optimization
- Memory management
- Mixed precision processing
- cuDNN benchmarking
- NVIDIA GPU with CUDA support
- Latest NVIDIA drivers
- CUDA toolkit installed
imageUpscaler process --input my_photos --output enhanced_photos --config config.json
{
"gpu_settings": {
"enabled": true,
"batch_size": 4,
"memory_limit": 0.8,
"optimization_level": "high",
"mixed_precision": true,
"cudnn_benchmark": true,
"clear_cache_after_batch": true
}
}
- Adjust batch_size based on your GPU memory
- Set memory_limit to 0.8 for optimal performance
- Enable mixed_precision for faster processing
- Use clear_cache_after_batch for large batches