Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
train_colossalai_teyvat.yaml 3.24 KB
Newer Older
Fazzie-Maqianli's avatar
[example] add diffusion inference (#1986)  
Fazzie-Maqianli committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122 
model:
  base_learning_rate: 1.0e-04
  target: ldm.models.diffusion.ddpm.LatentDiffusion
  params:
    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   # Note: different from the one we trained before
    conditioning_key: crossattn
    monitor: val/loss_simple_ema
    scale_factor: 0.18215
    use_ema: False

    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:
        image_size: 32 # unused
        from_pretrained: '/data/scratch/diffuser/stable-diffusion-v1-4/unet/diffusion_pytorch_model.bin'
        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_heads: 8
        use_spatial_transformer: True
        transformer_depth: 1
        context_dim: 768
        use_checkpoint: False
        legacy: False

    first_stage_config:
      target: ldm.models.autoencoder.AutoencoderKL
      params:
        embed_dim: 4
        from_pretrained: '/data/scratch/diffuser/stable-diffusion-v1-4/vae/diffusion_pytorch_model.bin'
        monitor: val/rec_loss
        ddconfig:
          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.FrozenCLIPEmbedder
      params:
        use_fp16: True

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: 256
        # - target: torchvision.transforms.RandomHorizontalFlip

lightning:
  trainer:
    accelerator: 'gpu' 
    devices: 2
    log_gpu_memory: all
    max_epochs: 10
    precision: 16
    auto_select_gpus: False
    strategy:
      target: lightning.pytorch.strategies.ColossalAIStrategy
      params:
        use_chunk: False
        enable_distributed_storage: True,
        placement_policy: cuda
        force_outputs_fp32: False

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

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