Diana_Pragmata_V2_ZIT_uint4_config.yaml

---
job: "extension"
config:
  name: "diana_pragmata_v2"
  process:
    - type: "diffusion_trainer"
      training_folder: "C:\\AI-Toolkit-Easy-Install\\AI-Toolkit\\output"
      sqlite_db_path: "./aitk_db.db"
      device: "cuda"
      trigger_word: "diprag"
      performance_log_every: 10
      network:
        type: "lora"
        linear: 16
        linear_alpha: 16
        conv: 16
        conv_alpha: 16
        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: "C:\\AI-Toolkit-Easy-Install\\AI-Toolkit\\datasets\\diana_pragmata_v2"
          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
          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: 2000
        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: true
        lr: 0.0002
        ema_config:
          use_ema: false
          ema_decay: 0.99
        skip_first_sample: true
        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-Turbo"
        quantize: true
        qtype: "uint4"
        quantize_te: true
        qtype_te: "qfloat8"
        arch: "zimage:turbo"
        low_vram: true
        model_kwargs: {}
        layer_offloading: true
        layer_offloading_text_encoder_percent: 1
        layer_offloading_transformer_percent: 0
        assistant_lora_path: "C:/Users/uthma/Downloads/zimage_turbo_training_adapter_v2.safetensors"
      sample:
        samples: []
meta:
  name: "[name]"
  version: "1.0"