job: extension
config:
  name: my_first_flux_lora_v1
  process:
  - type: sd_trainer
    training_folder: /workspace/output
    performance_log_every: 50
    device: cuda:0
    trigger_word: elmajjodi
    network:
      type: lora
      linear: 16
      linear_alpha: 16
    save:
      dtype: float16
      save_every: 250
      max_step_saves_to_keep: 4
    datasets:
    - folder_path: /workspace/dataset
      caption_ext: txt
      caption_dropout_rate: 0.05
      shuffle_tokens: false
      cache_latents_to_disk: true
      resolution:
      - 512
      - 768
      - 1024
    train:
      batch_size: 1
      steps: 1500
      gradient_accumulation_steps: 1
      train_unet: true
      train_text_encoder: false
      content_or_style: balanced
      gradient_checkpointing: true
      noise_scheduler: flowmatch
      optimizer: adamw8bit
      lr: 0.0001
      skip_first_sample: true
      ema_config:
        use_ema: true
        ema_decay: 0.99
      dtype: bf16
    model:
      name_or_path: black-forest-labs/FLUX.1-dev
      is_flux: true
      quantize: true
    sample:
      sampler: flowmatch
      sample_every: 250
      width: 1024
      height: 1024
      prompts:
      - '[trigger] a man holding a sign that says, ''this is a sign'''
      - '[trigger] A man holding a sign that says "I LOVE PROMPTS!"'
      - '[trigger] A man playing chess at the park, bomb going off in the background'
      - '[trigger] A man holding a coffee cup, in a beanie, sitting at a cafe'
      - '[trigger] In the style of TOK, a photo editorial avant-garde dramatic action
        pose of a person wearing 90s round wacky sunglasses pulling glasses down looking
        forward, in Tokyo with large marble structures and bonsai trees at sunset
        with a vibrant illustrated jacket surrounded by illustrations of flowers,
        smoke, flames, ice cream, sparkles, rock and roll'
      neg: ''
      seed: 42
      walk_seed: true
      guidance_scale: 4
      sample_steps: 20
meta:
  name: my_first_flux_lora_v1
  version: '1.0'