Testing Your Custom Generator

After you have finished training a model, we recommend creating 10 instance images at 512x512 pixels and 30 steps.

This will show you what the training retained and whether your model is overfit. You should then test your generator with a few simple prompts.

     If you notice that your images are including details from your original dataset that you did not want, you may be able to prompt them out. However, if testing the generator with prompts does not produce the desired results, you will need to start again. In this case, we recommend referring to our tutorials on curating datasets and training custom generators.