EVO 3: v0.44 (SD2.1 768): evo_car_D-adaptation-LoRA_SD21-768_v044.safetensors

Dataset: 44 images (x 30 repeats)

BLIP captioning

1320 cherry picked reg images

D-Adaptation

LR: 0.5

Constant with warmup (10%)

Train batch size: 4

First of a series of EVO brand cars LoRA models.

All training suggestions are welcome.

v0.741 first SDXL version, includes EVO 3 car, Cattedrale di Palermo square, Teatro Massimo & Palermo streets