How many images should I select to train a generator?
It is important to have a variety of unique images in your dataset. You must have at least 5 and no more than 100 images. Here are some general guidelines:
If the subject or style you are training is fairly commonplace and likely already exists in the dataset, you do not need many images. 6-10 is fine.
For complex subjects like avatars, vehicles, and animals, try to provide between 15-20 images. For simple subjects like plants, garments, and weapons, aim for 8-20 images.
Style training usually requires a more varied array of different subjects, and the images should not differ too much in aesthetics. Aim for 15-30 images, depending on your desired outcome.
The quality and variability of the images is more important than the exact number. Make sure your dataset does not include repeated or too similar images.
For more information, read our tutorials and check out our pre-created dataset.
If the subject or style you are training is fairly commonplace and likely already exists in the dataset, you do not need many images. 6-10 is fine.
For complex subjects like avatars, vehicles, and animals, try to provide between 15-20 images. For simple subjects like plants, garments, and weapons, aim for 8-20 images.
Style training usually requires a more varied array of different subjects, and the images should not differ too much in aesthetics. Aim for 15-30 images, depending on your desired outcome.
The quality and variability of the images is more important than the exact number. Make sure your dataset does not include repeated or too similar images.
For more information, read our tutorials and check out our pre-created dataset.
Updated on: 16/01/2023
Thank you!