YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Flux-2K-9B-64-05 LoRA

Style LoRA trained on FLUX.2-klein-base-9B with rank 64.

Details

  • Base model: black-forest-labs/FLUX.2-klein-base-9B
  • Trigger word: t01nspc_style
  • Network: LoRA (linear=64, linear_alpha=64, conv=16)
  • Training steps: 7000 (in progress)
  • Learning rate: 5e-05
  • Optimizer: adamw8bit
  • Dtype: bf16
  • Content/Style: balanced
  • Resolution: [512, 768, 1024]

Training Parameters

Parameter Value
Batch size 1
Noise scheduler flowmatch
Timestep type weighted
Loss type mse
Caption dropout 0.05
Weight decay 0.00015
Diff output preservation True

Checkpoints

Saved every 500 steps in checkpoints/.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support