Loading
Suggested 8 steps and cfg 1 for generation with this Lora.
Modellquelle
Quellenbeschreibung
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
Quellen
1 QuelleModellartefakte
1 ArtefaktkwFemaleBeta3_KREA2_v1.safetensors
safetensors · FP32 · 3,50 GB · SHA-256 a8971b44a80c…11ce · Civitai
HerunterladenQuellenauszüge
1 AuszugSource context: 212 downloads · Type LORA · Base model Krea 2
transformer_only: false
caption_dropout_rate: 0.0
ema removed
quantize: false
quantize_te: false