Loading
Suggested 8 steps and cfg 1 for generation with this Lora.
Fuente del modelo
Descripción de la fuente
The AI-Toolkit settings are as follows:
Optimizer: AdamW
Training Precision: fp32
Save Precision: float32
EPS: 1e-8
Learning rate: 8e-5
Linear: 256
Linear_alpha: 256
Resolution: 1024x1536
Batch Size: 1
training_seed: 1234
Fuentes
1 fuenteArtefactos del modelo
1 artefactokwFemaleBeta3_KREA2_v1.safetensors
safetensors · FP32 · 3,50 GB · SHA-256 a8971b44a80c…11ce · Civitai
DescargarExtractos de fuentes
1 extractoSource context: 212 downloads · Type LORA · Base model Krea 2
transformer_only: false
caption_dropout_rate: 0.0
ema removed
quantize: false
quantize_te: false