ModelsLab/Pepe FLUX - BS Pepe FLUX V1.0

Tags need to be explored to find the best ones, initial testing indicating that all though everything works, some work better than others. Try using style tags at the end of your prompt.Training settings: train: batch_size: 4 steps: 4000 gradient_accumulation_steps: 4 train_unet: true train_text_encoder: false content_or_style: balanced gradient_checkpointing: true noise_scheduler: flowmatch optimizer: adamw8bit lr: 0.0004 ema_config: use_ema: true ema_decay: 0.99 dtype: bf16