flux2-klein-4b-base-lora-vintage-book-cover-train-config.yaml

job: extension
config:
  name: flux2-klein-4b-lora-vintage-cover
  process:
  - type: diffusion_trainer
    training_folder: /home/dadler/projects/ai-toolkit/output
    sqlite_db_path: ./aitk_db.db
    device: cuda
    trigger_word: book cover
    performance_log_every: 10
    network:
      type: lora
      linear: 32
      linear_alpha: 32
      conv: 16
      conv_alpha: 16
      lokr_full_rank: true
      lokr_factor: -1
      network_kwargs:
        ignore_if_contains: []
    save:
      dtype: bf16
      save_every: 250
      max_step_saves_to_keep: 4
      save_format: diffusers
      push_to_hub: false
    datasets:
    - folder_path: /home/dadler/projects/ai-toolkit/datasets/vintage
      mask_path: null
      mask_min_value: 0.1
      default_caption: ''
      caption_ext: txt
      caption_dropout_rate: 0.05
      cache_latents_to_disk: true
      is_reg: false
      network_weight: 1
      resolution:
      - 512
      - 768
      - 1024
      controls: []
      shrink_video_to_frames: true
      num_frames: 1
      flip_x: false
      flip_y: false
      num_repeats: 1
      control_path_1: null
      control_path_2: null
      control_path_3: null
    train:
      batch_size: 1
      bypass_guidance_embedding: false
      steps: 3000
      gradient_accumulation: 1
      train_unet: true
      train_text_encoder: false
      gradient_checkpointing: true
      noise_scheduler: flowmatch
      optimizer: adamw8bit
      timestep_type: weighted
      content_or_style: balanced
      optimizer_params:
        weight_decay: 0.0001
      unload_text_encoder: false
      cache_text_embeddings: false
      lr: 0.0001
      ema_config:
        use_ema: false
        ema_decay: 0.99
      skip_first_sample: false
      force_first_sample: false
      disable_sampling: false
      dtype: bf16
      diff_output_preservation: false
      diff_output_preservation_multiplier: 1
      diff_output_preservation_class: person
      switch_boundary_every: 1
      loss_type: mse
    logging:
      log_every: 1
      use_ui_logger: true
    model:
      name_or_path: black-forest-labs/FLUX.2-klein-base-4B
      quantize: true
      qtype: qfloat8
      quantize_te: true
      qtype_te: qfloat8
      arch: flux2_klein_4b
      low_vram: false
      model_kwargs:
        match_target_res: false
      layer_offloading: false
      layer_offloading_text_encoder_percent: 1
      layer_offloading_transformer_percent: 1
    sample:
      sampler: flowmatch
      sample_every: 250
      width: 1024
      height: 1024
      samples:
      - prompt: '[trigger] of a woman with red hair, playing chess at the park, bomb
          going off in the background'
      - prompt: a horse is a DJ at a night club, fish eye lens, smoke machine, lazer
          lights, holding a martini [trigger]
      - prompt: '[trigger] a man showing off his cool new t shirt at the beach, a
          shark is jumping out of the water in the background'
      - prompt: 'woman playing the guitar, on stage, singing a song, laser lights,
          punk rocker [trigger] '
      - prompt: '[trigger] of a man holding a sign that says, ''this is a sign'''
      - prompt: '[trigger] where a bulldog, in a post apocalyptic world, with a shotgun,
          in a leather jacket, in a desert, with a motorcycle'
      neg: ''
      seed: 42
      walk_seed: true
      guidance_scale: 4
      sample_steps: 20
      num_frames: 1
      fps: 1
meta:
  name: flux2-klein-4b-lora-vintage-cover
  version: '1.0'