ColossalAI/examples/images/diffusion/configs/Teyvat/train_colossalai_teyvat.yaml

model:
  base_learning_rate: 1.0e-4
  target: ldm.models.diffusion.ddpm.LatentDiffusion
  params:
    parameterization: "v"
    linear_start: 0.00085
    linear_end: 0.0120
    num_timesteps_cond: 1
    log_every_t: 200
    timesteps: 1000
    first_stage_key: image
    cond_stage_key: txt
    image_size: 64
    channels: 4
    cond_stage_trainable: false
    conditioning_key: crossattn
    monitor: val/loss_simple_ema
    scale_factor: 0.18215
    use_ema: False # we set this to false because this is an inference only config

    scheduler_config: # 10000 warmup steps
      target: ldm.lr_scheduler.LambdaLinearScheduler
      params:
        warm_up_steps: [ 1 ] # NOTE for resuming. use 10000 if starting from scratch
        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
        f_start: [ 1.e-6 ]
        f_max: [ 1.e-4 ]
        f_min: [ 1.e-10 ]


    unet_config:
      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
      params:
        use_checkpoint: True
        use_fp16: True
        image_size: 32 # unused
        in_channels: 4
        out_channels: 4
        model_channels: 320
        attention_resolutions: [ 4, 2, 1 ]
        num_res_blocks: 2
        channel_mult: [ 1, 2, 4, 4 ]
        num_head_channels: 64 # need to fix for flash-attn
        use_spatial_transformer: True
        use_linear_in_transformer: True
        transformer_depth: 1
        context_dim: 1024
        legacy: False

    first_stage_config:
      target: ldm.models.autoencoder.AutoencoderKL
      params:
        embed_dim: 4
        monitor: val/rec_loss
        ddconfig:
          #attn_type: "vanilla-xformers"
          double_z: true
          z_channels: 4
          resolution: 256
          in_channels: 3
          out_ch: 3
          ch: 128
          ch_mult:
          - 1
          - 2
          - 4
          - 4
          num_res_blocks: 2
          attn_resolutions: []
          dropout: 0.0
        lossconfig:
          target: torch.nn.Identity

    cond_stage_config:
      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
      params:
        freeze: True
        layer: "penultimate"

data:
  target: main.DataModuleFromConfig
  params:
    batch_size: 16
    num_workers: 4
    train:
      target: ldm.data.teyvat.hf_dataset
      params:
        path: Fazzie/Teyvat
        image_transforms:
        - target: torchvision.transforms.Resize
          params:
            size: 512
        - target: torchvision.transforms.RandomCrop
          params:
            size: 512
        - target: torchvision.transforms.RandomHorizontalFlip

lightning:
  trainer:
    accelerator: 'gpu'
    devices: 2
    log_gpu_memory: all
    max_epochs: 2
    precision: 16
    auto_select_gpus: False
    strategy:
      target: strategies.ColossalAIStrategy
      params:
        use_chunk: True
        enable_distributed_storage: True
        placement_policy: cuda
        force_outputs_fp32: true
        min_chunk_size: 64

    log_every_n_steps: 2
    logger: True
    default_root_dir: "/tmp/diff_log/"
    # profiler: pytorch

  logger_config:
    wandb:
      target: loggers.WandbLogger
      params:
          name: nowname
          save_dir: "/tmp/diff_log/"
          offline: opt.debug
          id: nowname