Flux Version:
The LoRa was trained on just two single transformer blocks with a rank of 32, which allows for achieving such a small file size without any loss of quality. Since the LoRa is applied to only two blocks, it is less prone to bleeding effects.
The LoRa works best with a high LoRa weight, around 0.9.
The trigger word is 'Clover.'
SDXL Version:
The LoRa works best with a high LoRa weight, around 0.9.
The trigger word is 'Katya Clover.'