---
job: "extension"
config:
  name: "illumination"
  process:
    - type: "ui_trainer"
      training_folder: "/var/home/lucie/Bureau/ai-toolkit/output"
      sqlite_db_path: "./aitk_db.db"
      device: "cuda"
      trigger_word: null
      performance_log_every: 10
      network:
        type: "lora"
        linear: 8
        linear_alpha: 8
        conv: 0
        conv_alpha: 0
        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: "/var/home/lucie/Bureau/ai-toolkit/datasets/illuminations"
          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: true
          is_reg: false
          network_weight: 1
          resolution:
            - 512
          controls: []
          shrink_video_to_frames: true
          num_frames: 1
          do_i2v: true
      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: true
        lr: 0.0002
        ema_config:
          use_ema: false
          ema_decay: 0.99
        skip_first_sample: true
        disable_sampling: true
        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: "uint4"
        quantize_te: true
        qtype_te: "uint4"
        arch: "qwen_image"
        low_vram: true
        model_kwargs: {}
      sample:
        sampler: "flowmatch"
        sample_every: 250
        width: 1024
        height: 1024
        samples:
          - prompt: "woman with red hair, playing chess at the park, bomb going off in the background"
          - prompt: "a woman 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: "woman 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: 4
        sample_steps: 25
        num_frames: 1
        fps: 1
meta:
  name: "[name]"
  version: "1.0"