How do I get as much detail as the images I used to build my dataset?
If you are struggling to get the level of detail in your dataset, here are a few things you can check:
- Guidance: Try increasing your guidance to 9 or 10.
- Regularization Class: Perhaps the regularization class isn’t quite optimal, so consider retraining on a new one.
- Sampling Steps: It is possible you are using too few sampling steps - or too many. Try to keep your steps between 30-50. In cases of finelinework, consider up to 80.
- Dataset images: It is possible there are grainy images in your dataset, or that your generator is overfit. In this case, it is best to retrain with a different curation of images.
- Overfitting: In some situations overfitting can lead to issues in your output, and may make your images grainy. Be sure that youre training steps, learning rate, and dataset are consistent with our guides.
Take a walkthrough of a starter generator here.
- Guidance: Try increasing your guidance to 9 or 10.
- Regularization Class: Perhaps the regularization class isn’t quite optimal, so consider retraining on a new one.
- Sampling Steps: It is possible you are using too few sampling steps - or too many. Try to keep your steps between 30-50. In cases of finelinework, consider up to 80.
- Dataset images: It is possible there are grainy images in your dataset, or that your generator is overfit. In this case, it is best to retrain with a different curation of images.
- Overfitting: In some situations overfitting can lead to issues in your output, and may make your images grainy. Be sure that youre training steps, learning rate, and dataset are consistent with our guides.
Take a walkthrough of a starter generator here.
Updated on: 16/01/2023
Thank you!