config.yaml

config:
  name: flux_dev_terragen2
  process:
  - datasets:
    - cache_latents_to_disk: true
      caption_dropout_rate: 0.2
      caption_ext: txt
      folder_path: /root/lorahub/flux_dev_terragen2/dataset
      resolution:
      - 512
      - 768
      - 1024
      shuffle_tokens: false
      token_dropout_rate: 0.01
    device: cuda:0
    model:
      is_flux: true
      name_or_path: black-forest-labs/FLUX.1-dev
      quantize: true
      text_encoder_bits: 8
    network:
      linear: 42
      linear_alpha: 42
      transformer_only: true
      type: lora
    performance_log_every: 500
    sample:
      height: 704
      neg: ''
      prompts:
      - a volcano in the background, a serene lake in the foreground [trigger]
      - a huge buddha statue on a mountain, surrounded by peaceful nature [trigger]
      - a man walking through a park during sunset [trigger]
      - sci-fi desert landscape with various planets in the sky[trigger]
      - a passanger plane above the clouds [trigger]
      - colorful alien landscape with pyraminds [trigger]
      sample_every: 500
      sample_steps: 25
      sampler: flowmatch
      seed: 42
      walk_seed: true
      width: 1344
    save:
      dtype: float16
      max_step_saves_to_keep: 3
      save_every: 500
      save_format: diffusers
    train:
      batch_size: 1
      dtype: bf16
      ema_config:
        ema_decay: 0.99
        use_ema: true
      gradient_accumulation_steps: 1
      gradient_checkpointing: true
      linear_timesteps: true
      loss_type: mse
      lr: 0.0002
      noise_scheduler: flowmatch
      optimizer: adamw8bit
      reg_weight: 1.0
      steps: 3000
      target_noise_multiplier: 1.0
      train_text_encoder: false
      train_unet: true
    training_folder: /root/lorahub
    trigger_word: TRGN, 3D
    type: sd_trainer
job: extension
meta:
  description: Trained on Terragen 2 renders for an old-school 3D look