Paid download in my crypto shop [$3]: https://aidoll.fun/?product=lora-of-india-woollard-yonger-for-sd1-5
-------------------------------------------------------------------------------------------------------------
LoRA of Australian fashion model and Instagram star India Woollard.
LoRA trained on her photos made around 2017, when she was 12 years old.
Trigger: AIDA_LoRA_InW2017
Best LoRA values: 0.77-0.97
This LoRA trained using kohya_ss on 60 images 768×768 for 2 epochs 1560 steps each with manually enhanced blip2 and/or llava captions and without regularization images.Source model: ‘v1-5-pruned-emaonly’ checkpoint (SD1.5), so this LoRA should works well with most of Stable Diffusion v1.5 forks and mixes.Learning rate: 2e-05 or 0.00001.Precision: fp16.LR Scheduler: constant_with_warmup.LR warmup: 30%.
