Edit model card
Training settings
- Training steps: 3000
- Learning rate: 8e-4
- Effective batch size: 1
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 1
- Prediction type: flow-matching
- Rescaled betas zero SNR: False
- Optimizer: adamw_bf16
- Precision: Pure BF16
- Gradient Precision: FP32
- Lora type: lycoris
Model tree for thwri/david-bowie-flux