job: extension
config:
  name: hardbody
  process:
  - type: diffusion_trainer
    training_folder: /data/app/output
    sqlite_db_path: /data/app/aitk_db.db
    device: cuda
    trigger_word: null
    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: 500
      max_step_saves_to_keep: 4
      save_format: diffusers
      push_to_hub: false
    datasets:
    - folder_path: /data/app/datasets/body_v01
      mask_path: null
      mask_min_value: 0.1
      default_caption: curvy female body
      caption_ext: txt
      caption_dropout_rate: 0.05
      cache_latents_to_disk: false
      is_reg: false
      network_weight: 1
      resolution:
      - 512
      - 768
      - 1024
      controls: []
      shrink_video_to_frames: true
      num_frames: 1
      do_i2v: true
      flip_x: false
      flip_y: false
    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
      do_differential_guidance: true
      differential_guidance_scale: 3
    model:
      name_or_path: Tongyi-MAI/Z-Image-Turbo
      quantize: true
      qtype: qfloat8
      quantize_te: true
      qtype_te: qfloat8
      arch: zimage:turbo
      low_vram: false
      model_kwargs: {}
      layer_offloading: false
      layer_offloading_text_encoder_percent: 1
      layer_offloading_transformer_percent: 1
      assistant_lora_path: ostris/zimage_turbo_training_adapter/zimage_turbo_training_adapter_v2.safetensors
    sample:
      sampler: flowmatch
      sample_every: 500
      width: 512
      height: 512
      samples:
      - prompt: a woman holding a coffee cup, in a beanie, sitting at a cafe, shorts
          and tight tanktop
      - prompt: woman playing the guitar, on stage, singing a song, laser lights,
          punk rocker
      - prompt: a naked woman holding a sign that says, 'hardbody'
      - prompt: solo, full body, standing, front view, completely nude, voluptuous
          curvy woman, huge natural breasts, detailed nipples, oiled shiny skin, glossy
          wet body, thick thighs, navel piercing, smooth tanned skin, neutral expression,
          gray studio background, soft lighting, photorealistic, ultra detailed, 8k
      - prompt: ''
      - prompt: beautiful nude woman, standing slightly turned three-quarter view,
          massive breasts, erect nipples, oiled glossy skin, wide hips, thick thighs,
          navel piercing, shiny bronze skin, full body, studio gray background, high
          detail skin texture, photorealistic, masterpiece
      - prompt: ''
      - prompt: curvy nude female model, full body portrait, very large natural breasts,
          shiny oiled skin, detailed anatomy, thick legs, standing pose, neutral face,
          professional studio photography, ultra realistic, highres
      neg: ''
      seed: 42
      walk_seed: true
      guidance_scale: 1
      sample_steps: 8
      num_frames: 1
      fps: 1
meta:
  name: hardbody
  version: '1.0'