Related notes
LoRA training notes
Learn the decisions behind a focused dataset, useful captions and an honest evaluation of your custom model.
How to train a LoRA modelA complete starting point, from choosing a concept to comparing the final adapter.How many images do you need?Choose useful variation rather than relying on one universal image count.A practical LoRA captioning guideSeparate the concept from changing details, with character, style and product examples.Training steps without the guessworkUnderstand steps, learning rate and overfitting before changing advanced settings.How to evaluate a trained LoRATest new prompts, compare a baseline and document useful failures.