z-image-base-lora

job: extension
config:
  name: incredible_z_v1
  process:
  - type: diffusion_trainer
    training_folder: E:\RemoteComfyUI\ai-toolkit\output
    sqlite_db_path: E:\RemoteComfyUI\ai-toolkit\aitk_db.db
    device: cuda
    trigger_word: null
    performance_log_every: 10
    network:
      type: lora
      linear: 16
      linear_alpha: 16
      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: 16
      save_format: diffusers
      push_to_hub: false
    datasets:
    - folder_path: E:\RemoteComfyUI\ai-toolkit\datasets/incredible_z
      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:
      - 512
      - 768
      - 1024
      controls: []
      shrink_video_to_frames: true
      num_frames: 1
      flip_x: false
      flip_y: false
      num_repeats: 1
    train:
      batch_size: 1
      bypass_guidance_embedding: false
      steps: 5000
      gradient_accumulation: 1
      train_unet: true
      train_text_encoder: false
      gradient_checkpointing: true
      noise_scheduler: flowmatch
      optimizer: prodigyopt
      timestep_type: weighted
      content_or_style: balanced
      optimizer_params:
        weight_decay: 0.01
      unload_text_encoder: false
      cache_text_embeddings: true
      lr: 1
      ema_config:
        use_ema: false
        ema_decay: 0.99
      skip_first_sample: false
      force_first_sample: false
      disable_sampling: true
      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: Tongyi-MAI/Z-Image
      quantize: false
      qtype: qfloat8
      quantize_te: false
      qtype_te: qfloat8
      arch: zimage
      low_vram: false
      model_kwargs: {}
      layer_offloading: false
      layer_offloading_text_encoder_percent: 1
      layer_offloading_transformer_percent: 1
    sample:
      sampler: flowmatch
      sample_every: 500
      width: 1024
      height: 1024
      samples:
      - prompt: 'parr analog film photo sexy The light source faces parr directly.
          It evenly illuminates the face, minimizing shadows and hiding skin imperfections.
          Shot on a Canon EOS R5 with an 85mm lens at f/1.4. diffuse lighting with
          soft, creamy bokeh in the background . faded film, desaturated, 35mm photo,
          grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed,
          found footage Outfit and Accessories: A white cropped shirt, a red and black
          plaid mini-skirt, black fishnet stockings, and black platform high heels
          with ankle straps. Black cat ears are worn on the head. Setting: A park
          with a gravel path, green grass, and numerous trees. Black park benches
          are visible in the background. Pose: The person is standing with their body
          angled slightly to the side, looking upward and away from the camera. Their
          hands are raised to their neck and collar area.'
      neg: ''
      seed: 42
      walk_seed: true
      guidance_scale: 4
      sample_steps: 30
      num_frames: 1
      fps: 1
meta:
  name: incredible_violet_z_v7
  version: '1.0'