configs/gaussiandreamer-sd.yaml

name: "gaussiandreamer-sd"
tag: "${rmspace:${system.prompt_processor.prompt},_}"
exp_root_dir: "outputs"
seed: 0
 
data_type: "random-camera-datamodule"
data:
  batch_size: 4
  eval_camera_distance: 4.0
  camera_distance_range: [1.5, 4.0]
  light_sample_strategy: "dreamfusion3dgs"
  height: 1024
  width: 1024
  eval_height: 1024
  eval_width: 1024
  # elevation_range: [-10 , 80]
system_type: "gaussiandreamer-system"
system:
  radius: ${data.eval_camera_distance}
  sh_degree: 0
  prompt_processor_type: "stable-diffusion-prompt-processor"
  prompt_processor:
    pretrained_model_name_or_path: "stabilityai/stable-diffusion-2-1-base"
    prompt: ???
    negative_prompt: "ugly, bad anatomy, blurry, pixelated obscure, unnatural colors, poor lighting, dull, and unclear, cropped, lowres, low quality, artifacts, duplicate, morbid, mutilated, poorly drawn face, deformed, dehydrated, bad proportions, unfocused"

  guidance_type: "stable-diffusion-guidance"
  guidance:
    pretrained_model_name_or_path: "stabilityai/stable-diffusion-2-1-base"
    guidance_scale: 100.
    weighting_strategy: sds
    min_step_percent: 0.02
    max_step_percent: 0.98
    grad_clip: [0,1.5,2.0,1000]

  loggers:
    wandb:
      enable: false
      project: 'threestudio'
      name: None

  loss:
    lambda_sds: 1.
    lambda_sparsity: 1.
    lambda_opaque: 0.0
  optimizer:
    name: Adam
    args:
      lr: 0.001
      betas: [0.9, 0.99]
      eps: 1.e-15

trainer:
  max_steps: 1200
  log_every_n_steps: 1
  num_sanity_val_steps: 0
  val_check_interval: 100
  enable_progress_bar: true
  precision: 16-mixed

checkpoint:
  save_last: true # save at each validation time
  save_top_k: -1
  every_n_train_steps: ${trainer.max_steps}