# Training configuration; local asset paths normalized for publication.
# model_name selects shared VAE/text assets; fun_control_model_path selects the trained DiT.
infra:
  expected_world_size: 16
  expected_nodes: 2
  expected_gpus_per_node: 8
  required_gpu_name: H100
  sharding_strategy: hybrid_full
  mixed_precision: true
  vae_dtype: float32
  gradient_checkpointing: true
  generator_fsdp_wrap_strategy: size
  real_score_fsdp_wrap_strategy: size
  fake_score_fsdp_wrap_strategy: size
  text_encoder_fsdp_wrap_strategy: size
model_kwargs:
  model_name: Wan2.2-TI2V-5B
  fun_control_model_path: models/Wan2.2-Fun-5B-Control
  timestep_shift: 5.0
  num_frame_per_block: 8
  local_attn_size: -1
  control_raw_frames: 93
checkpoints:
  generator_ckpt: null
  real_score_ckpt: null
  fake_score_ckpt: null
algorithm:
  trainer: score_distillation
  distribution_loss: dmd
  generator_is_causal: false
  real_score_is_causal: false
  fake_score_is_causal: false
  all_causal: false
  backward_simulation: true
  independent_first_frame: false
  ts_schedule: false
  real_guidance_scale: 3.0
  fake_guidance_scale: 0.0
training:
  lr: 1.0e-05
  lr_critic: 2.0e-06
  weight_decay: 0.0
  beta1: 0.0
  beta2: 0.999
  beta1_critic: 0.0
  beta2_critic: 0.999
  batch_size: 1
  gradient_accumulation_steps: 2
  ema_weight: 0.99
  ema_start_step: 200
  log_iters: 100
  max_checkpoints: 20
  max_iters: 3000
  gc_interval: 100
  dfake_gen_update_ratio: 5
  min_num_training_frames: 24
  num_training_frames: 24
  slice_last_frames: 24
data:
  data_path: data/depth_video_5k/manifest.jsonl
  eval_data_path: data/depth_video_5k/manifest.jsonl
  control_manifest: data/depth_video_5k/manifest.jsonl
  eval_control_manifest: data/depth_video_5k/manifest.jsonl
  control_raw_frames: 93
  control_min_temporal_difference: 0.0001
  control_num_workers: 2
  image_or_video_shape:
  - 1
  - 24
  - 48
  - 30
  - 52
  full_ref_mode: zero_through_ref_conv
inference:
  sampling_steps: 4
  guidance_scale: 1.0
  inference_guidance_scale: 1.0
  sink_size: 0
  multi_shot_rope_offset: 0
evaluation:
  interval: -1
  num_frames: 24
  use_ema: false
  val_batch_size: 1
  save_latents_only: true
adapter:
  type: lora
  rank: 64
  alpha: 64
  dropout: 0.0
  apply_to_critic: true
  verbose: false
logging:
  seed: 17
  wandb_entity: null
  wandb_project: LongLive-WanFun5B-Control-DMD