ABARA Style Manga Lora [Tsutomu Nihei] Z-Image v2

드디어 이걸 성공적으로 작동시켰습니다. 내 트레이닝 설정과 데이터셋 반복에 대한 노트를 내 프로필에 저장할 예정입니다.

노트:

모든 이미지를 수동으로 크기 조정

이미지 배치를 300개 이상에서 32개로 줄임
캡션 또는 태그 없음(스타일에 더 적합)

"ABARA" 트리거 단어 추가

ABARA LoRA 데이터셋
https://drive.google.com/drive/folders/1EwOoWwQfycye9w4gehE8wViY4TryLR4g?usp=sharing

CONFIG: Ostris AI Toolkit 사용

---
job: "extension"
config:
  name: "abara-v2"
  process:
    - type: "diffusion_trainer"
      training_folder: "C:\\Ostris-AI-Toolkit\\AI-Toolkit\\output"
      sqlite_db_path: "./aitk_db.db"
      device: "cuda"
      trigger_word: "abara"
      performance_log_every: 10
      network:
        type: "lora"
        linear: 128
        linear_alpha: 128
        conv: 128
        conv_alpha: 128
        lokr_full_rank: true
        lokr_factor: -1
        network_kwargs:
          ignore_if_contains: []
      save:
        dtype: "bf16"
        save_every: 600
        max_step_saves_to_keep: 16
        save_format: "diffusers"
        push_to_hub: false
      datasets:
        - folder_path: "C:\\Ostris-AI-Toolkit\\AI-Toolkit\\datasets/abara_ready"
          mask_path: null
          mask_min_value: 0.1
          default_caption: ""
          caption_ext: "txt"
          caption_dropout_rate: 0
          cache_latents_to_disk: true
          is_reg: false
          network_weight: 1
          resolution:
            - 1536
          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: 6000
        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: 0.0001
        ema_config:
          use_ema: false
          ema_decay: 0.99
        skip_first_sample: true
        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"
      model:
        name_or_path: "Tongyi-MAI/Z-Image-Turbo"
        quantize: false
        qtype: "qfloat8"
        quantize_te: false
        qtype_te: "qfloat8"
        arch: "zimage:turbo"
        low_vram: true
        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: 250000
        width: 1536
        height: 1536
        samples:
          - prompt: "man with red hair, playing chess at the park, bomb going off in the background"
          - prompt: "a man holding a coffee cup, in a beanie, sitting at a cafe"
          - prompt: "a horse is a DJ at a night club, fish eye lens, smoke machine, lazer lights, holding a martini"
          - prompt: "a man showing off his cool new t shirt at the beach, a shark is jumping out of the water in the background"
          - prompt: "a bear building a log cabin in the snow covered mountains"
          - prompt: "man playing the guitar, on stage, singing a song, laser lights, punk rocker"
          - prompt: "hipster man with a beard, building a chair, in a wood shop"
          - prompt: "photo of a man, white background, medium shot, modeling clothing, studio lighting, white backdrop"
          - prompt: "a man holding a sign that says, 'this is a sign'"
          - prompt: "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: 1
        sample_steps: 8
        num_frames: 1
        fps: 1
meta:
  name: "[name]"
  version: "1.0"