defaults:
  - algorithm: df_video_worldmemminecraft
  - experiment: exp_video
  - dataset: video_minecraft

dataset:
  n_frames_valid: 100
  validation_multiplier: 1
  use_plucker: true
  customized_validation: true
  condition_similar_length: 8
  padding_pool: 10
  focal_length: 0.35
  save_dir: data/test_pumpkin
  add_frame_timestep_embedder: true
  pos_range: 0.5
  angle_range: 30

experiment:
  tasks: [interactive]
  training:
    data:
      num_workers: 4
  validation:
    batch_size: 1
    limit_batch: 1
    data:
      num_workers: 4
  load_vae: false
  load_t_to_r: false
  zero_init_gate: false
  only_tune_refer: false
  diffusion_path: checkpoints/diffusion_only.ckpt
  vae_path: checkpoints/vae_only.ckpt
  pose_predictor_path: checkpoints/pose_prediction_model_only.ckpt
  customized_load: true

algorithm:
  n_tokens: 8
  context_frames: 90
  pose_cond_dim: 5
  use_plucker: true
  focal_length: 0.35
  customized_validation: true
  condition_similar_length: 8
  log_video: true
  relative_embedding: true
  cond_only_on_qk: true
  add_pose_embed: false
  use_domain_adapter: false
  use_reference_attention: true
  add_frame_timestep_embedder: true
  is_interactive: true
  diffusion:
    sampling_timesteps: 20

debug: false