job: extension
config:
  name: sambitv2_wan21_14b_lora_v1
  process:
  - type: sd_trainer
    training_folder: output
    device: cuda:0
    trigger_word: ''
    network:
      type: lora
      linear: 32
      linear_alpha: 32
    save:
      dtype: float16
      save_every: 250
      max_step_saves_to_keep: 4
      push_to_hub: false
    datasets:
    - folder_path: /root/.cache/huggingface/hub/datasets--sam2ai--sam_ai_sd/snapshots/bf7aa55bc939007e4fb74058fa3603d680f1c338
      caption_ext: txt
      caption_dropout_rate: 0.05
      shuffle_tokens: false
      cache_latents_to_disk: true
      resolution:
      - 632
    train:
      batch_size: 1
      steps: 3000
      gradient_accumulation: 1
      train_unet: true
      train_text_encoder: false
      gradient_checkpointing: true
      noise_scheduler: flowmatch
      timestep_type: sigmoid
      optimizer: adamw8bit
      lr: 0.0001
      optimizer_params:
        weight_decay: 0.0001
      ema_config:
        use_ema: true
        ema_decay: 0.99
      dtype: bf16
      unload_text_encoder: true
    model:
      name_or_path: Wan-AI/Wan2.1-T2V-14B-Diffusers
      arch: wan21
      quantize: true
      quantize_te: true
      low_vram: true
    sample:
      sampler: flowmatch
      sample_every: 250
      width: 832
      height: 480
      num_frames: 40
      fps: 15
      prompts:
      - '[trigger] in a red robe and a red hat, on stage, singing a song, laser lights,
        punk rocker'
      - '[trigger] playing the guitar, on stage, singing a song, laser lights, punk
        rocker'
      - '[trigger] in neon face paint, surrounded by fog, jumping off an amp, chaotic
        punk rock energy, crowd surfing'
      - '[trigger] on an underground club stage, graffiti-covered walls, performing
        a fast punk rock song, flashing lights'
      - '[trigger] on a rooftop stage at night, city skyline in the background, performing
        a rebellious punk anthem'
      - '[trigger] inside a packed venue with mohawks and piercings in the crowd,
        energetic punk rock performance'
      - '[trigger] in a medieval punk mashup, armored guitar, fiery torches around
        the stage, fusion of old and new'
      neg: ''
      seed: 42
      walk_seed: true
      guidance_scale: 5
      sample_steps: 30
meta:
  name: sambitv2_wan21_14b_lora_v1
  version: '1.0'