Hugging Face's logo

Spaces:
basso4
/
fptvton1
Running on Zero

App Files Community
1
fptvton1
File size: 2,184 Bytes 
adf1965
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
model:
  base_learning_rate: 3e-05
  target: ldm.models.diffusion.control.ControlLDM
  params:
    linear_start: 0.00085
    linear_end: 0.0120
    log_every_t: 200
    timesteps: 1000
    image_size: 64
    channels: 4
    u_cond_percent: 0.2
    scale_factor: 0.18215
    use_ema: False

    control_stage_config:
      target: ldm.models.diffusion.control.ControlNet
      params:
        use_checkpoint: True
        in_channels: 9
        hint_channels: 5
        model_channels: 320
        attention_resolutions: [ 4, 2, 1 ]
        num_res_blocks: 2
        channel_mult: [ 1, 2, 4, 4 ]
        num_head_channels: 64
        transformer_depth: 1
        context_dim: 768

    unet_config:
      target: ldm.models.diffusion.control.ControlledUnetModel
      params:
        image_size: 32 # unused
        in_channels: 9
        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: True
        legacy: False
        add_conv_in_front_of_unet: False

    first_stage_config:
      target: ldm.models.autoencoder.AutoencoderKL
      params:
        embed_dim: 4
        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.FrozenCLIPImageEmbedder

data:
  target: train.DataModuleFromConfig
  params:
      batch_size: 2
      wrap: False
      train:
          target: ldm.data.image_dresscode.OpenImageDataset
          params:
              state: train
              dataset_dir: datasets/dresscode
              

lightning:
  trainer:
    max_epochs: 80
    num_nodes: 1
    profiler: "simple"
    accelerator: 'ddp'
    gpus: "0,1"