Skip to main content

Getting Started with Vision FX

Vision FX uses AI models to edit and transform images. This guide will help you get up and running quickly.

What you need before starting​

Before you can generate anything, you need to install at least one AI model.

AI models are not included by default. They are downloaded through the Model Hub based on your hardware and preferences.

Step 1 - Install a model​

Open the Model Hub and install a model:

  1. Click Get Models
  2. Browse available models
  3. Select one that matches your hardware
  4. Click Install

Once installed, the model variant will be available for selection in AI Engine Settings.

Step 2 - Select your model​

After installing a model, you need to select how it will run:

  1. Open AI Engine Settings
  2. Choose your installed model
  3. Select a model variant optimized for your hardware

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

The app may also suggest optimizations to improve performance or stability.

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

Step 3 - Edit or transform an existing image​

  1. Import an image
  2. Describe what you want to change (style, colors, background, etc.)
  3. Adjust settings as needed
  4. Click Generate

(New version coming soon)

Understanding the workflow​

All workflows follow the same general process:

  1. Choose a model
  2. Set your input (text or image)
  3. Adjust settings
  4. Click Generate
  5. Refine and iterate

Generating updates the current image. You can adjust settings, try different prompts or presets, and generate again to refine your result.

If you want to explore different directions, duplicate an image before generating to keep your original.

Tips for best results​

  • Start simple, or use example prompts for inspiration. You can also explore prompts shared online.
  • Generate multiple results to compare and find what works best.
  • Adjust settings and generate again to refine your results.
  • Try different models if results vary. Each model has its own strengths.
  • If generation is slow or fails, try a different model or variant, switch processing method (CPU or GPU), or enable options like reduced GPU memory usage if available.

Troubleshooting​

App controls are disabled

  • Select a model in AI Engine Settings to enable generation features.

No models available

Generation fails, is slow, or not working as expected

  • Try a different model or variant, or switch processing method (CPU or GPU).
  • Reduce image size in Image Settings.
  • Enable options like reduced GPU memory usage if available.

Results are not what you expected

  • Adjust your prompt or try a preset.
  • Generate multiple results and refine your settings.

What's next?​