Skip to main content

Model Settings

What are Model Settings?​

Model Settings lets you choose how the AI model runs on your system. This includes selecting a model, choosing a variant optimized for your hardware, and adjusting performance-related options.

You can open Model Settings from AI Engine > Settings.

Choosing a model​

Select the model you want to use from your installed models.

Different models offer different strengths, styles, quality levels, and performance characteristics. Some models are optimized for speed, while others focus on higher quality or more advanced capabilities.

If you're unsure, start with a recommended model.

Model variants​

When you install a model, you install one variant at a time. Each variant is an optimized version of the model designed for specific hardware and performance needs.

In Model Settings, you will only see the variants that you have installed.

If needed, you can install additional variants of the same model from the Model Hub and switch between them.

Choosing the right variant affects:

  • Performance (speed)
  • Memory usage
  • Compatibility with your system
  • Available processing methods, such as CPU or GPU
  • Available features and settings

Some features, such as Negative Prompt, Text Guidance, Style Reference, or the Reduce memory usage option, may only be available with supported models or variants.

If you're unsure, choose a variant that is marked as compatible with your system. You can install additional variants later if needed.

If a configuration is not working well or is slow, try installing a different variant of the same model.

Common variant types​

You may see different variant types when selecting a model. These are optimized for different hardware and performance needs.

CUDA / PyTorch (NVIDIA GPUs)​

Optimized for NVIDIA graphics cards. This is usually the fastest option if you have a supported NVIDIA GPU.

  • Prefer BF16 over FP16 if the model and your system support it, for the best quality.
  • Enable reduced GPU memory usage if you encounter memory issues.

ONNX (DirectML / AMD GPUs)​

Optimized for AMD GPUs and compatible DirectML systems.

  • Works across a wide range of AMD hardware.
  • On some systems, increasing GPU memory allocation in the BIOS can improve performance.
  • Enable reduced memory usage if available and you encounter memory issues.

OpenVINO FP16 (Intel GPUs and Intel/AMD CPUs)​

Optimized for Intel GPUs and CPU-based processing.

  • Suitable for Intel GPUs.
  • Recommended when running supported models on CPU, including Intel and AMD CPUs.
  • Good general-purpose option when GPU acceleration is not available.
  • Enable reduced memory usage if available and you encounter memory issues.

OpenVINO INT8 (select Intel CPUs)​

Optimized for faster CPU performance on supported Intel CPUs.

  • A good choice for CPU inference when supported by your Intel processor.
  • Often faster than FP16 on compatible Intel CPUs.
  • May slightly reduce image quality compared to FP16.
  • Enable reduced memory usage if available and you encounter memory issues.

Processing methods​

Depending on the selected variant, the app will propose available processing methods (such as CPU or GPU) and check whether your selection is compatible.

  • GPU: Faster performance, recommended when available
  • CPU: More compatible, but generally slower

Additional processing methods may be available depending on your hardware.

Compatibility and recommendations​

The app evaluates your configuration and provides guidance based on your hardware.

  • Some configurations may not be supported
  • Some may work but require more memory than available
  • Compatible options are highlighted to help you choose

If you're unsure, follow the compatible options shown in the app.

Model-dependent features​

Some features are only available with supported models.

Depending on the selected model, Vector FX may show, hide, or disable controls such as:

  • Negative Prompt
  • Text Guidance
  • Style Reference
  • Reduce memory usage

If a feature is not available, it may be because the selected model does not support it.

Performance and quality​

Different configurations offer different trade-offs:

  • GPU vs CPU: GPU is faster, CPU is more widely supported
  • FP16/BF16 vs INT8: FP16 and BF16 generally preserve more model precision, while INT8 can improve CPU performance
  • Model choice: Some models prioritize speed, while others prioritize quality or specific creative styles

You can experiment with different configurations to find what works best for your needs.

Advanced options​

Some models provide additional options to improve performance, stability or reduce memory usage.

Reduce memory usage​

  • Reduces the amount of system memory or GPU memory required while the model is running
  • Can help run supported models on systems with limited available memory
  • May affect processing speed, depending on the selected model and configuration
  • Some memory-saving methods may slightly reduce image quality
  • Available only with supported models and configurations

The option may be enabled automatically when needed, but you can adjust it manually when available.

Tips​

  • Start with compatible options if you're unsure.
  • Prefer GPU-based variants when available for better performance.
  • If something is slow or not working, try a different variant or processing method.
  • Try different models to compare speed, quality, and style.
  • Small configuration changes can significantly affect results.