job: extension
config:
  name: headshot-qwen
  process:
  - type: ui_trainer
    training_folder: /workspace/ai-toolkit/output
    sqlite_db_path: /workspace/ai-toolkit/aitk_db.db
    device: cuda
    trigger_word: headshot
    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: /workspace/ai-toolkit/datasets/headshot
      control_path: null
      mask_path: null
      mask_min_value: 0.1
      default_caption: ''
      caption_ext: txt
      caption_dropout_rate: 0.05
      cache_latents_to_disk: false
      is_reg: false
      network_weight: 1
      resolution:
      - 1024
      controls: []
      shrink_video_to_frames: true
      num_frames: 1
    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
      lr: 0.0001
      ema_config:
        use_ema: false
        ema_decay: 0.99
      skip_first_sample: false
      disable_sampling: false
      dtype: bf16
      diff_output_preservation: false
      diff_output_preservation_multiplier: 1
      diff_output_preservation_class: person
    model:
      name_or_path: Qwen/Qwen-Image
      quantize: true
      qtype: qfloat8
      quantize_te: true
      qtype_te: qfloat8
      arch: qwen_image
      low_vram: false
      model_kwargs: {}
    sample:
      sampler: flowmatch
      sample_every: 250
      width: 1328
      height: 1328
      samples:
      - prompt: headshot, woman product designer, early-30s, medium-brown skin, natural
          curls in low puff, clear round acetate glasses, subtle makeup, light freckles,
          neutral gray studio background, solo, looking at viewer, relaxed professional
          expression, closed mouth, softbox 3/4 key lighting, shallow depth of field,
          sharp focus on eyes, simple background, photorealistic, high detail
      - prompt: headshot, high elf mage, pale luminous skin, long pointed ears, silver
          hair in loose braid, amber irises faintly glowing, delicate moon-silver
          circlet, faint arcane sigils on cheeks, neutral gray studio background,
          solo, looking at viewer, serene expression, closed mouth, soft studio light,
          crisp detail on pores and jewelry, photorealistic, high detail
      neg: ''
      seed: 42
      walk_seed: true
      guidance_scale: 4
      sample_steps: 50
      num_frames: 1
      fps: 1
meta:
  name: headshot-qwen
  version: '1.0'