Hugging Face's logo

Spaces:
tmaham
/
DS-Fusion-Express
Runtime error

App Files Community
1
DS-Fusion-Express
File size: 2,878 Bytes 
ca4133a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
model:
  base_learning_rate: 1.0e-5 #1e-4
  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: "caption"
    image_size: 64 # 32
    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
    weight_disc: 0.01

    unet_config:
      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
      params:
        image_size: 64 # 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_heads: 8
        use_spatial_transformer: True
        transformer_depth: 1
        context_dim: 768 # 1280
        use_checkpoint: True
        legacy: 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: 512 #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
    
    discriminator_config:
      target: ldm.modules.discriminator.Discriminator64

data:
  target: main.DataModuleFromConfig
  params:
    batch_size: 1
    num_workers: 32
    wrap: false
    train:
      target: ldm.data.rasterizer.Rasterizer
      params:
        img_size: 256
        text: "R"
        style_word: "DRAGON"
        data_path: "data/cat"
        alternate_glyph: None
        num_samples: 2001
        make_black: False
        one_font: False
        full_word: False
        font_name: "Garuda-Bold.ttf"
        just_use_style: false
        use_alt: False
    validation:
      target: ldm.data.rasterizer.Rasterizer
      params:
        img_size: 256
        text: "R"
        style_word: "DRAGON"
        data_path: "data/cat"
        alternate_glyph: None
        num_samples: 5
        make_black: False
        one_font: False
        full_word: False
        font_name: "Garuda-Bold.ttf"
        just_use_style: false
        use_alt: False

lightning:
  modelcheckpoint:
    params:
      every_n_train_steps: 200
  callbacks:
    image_logger:
      target: main.ImageLogger
      params:
        batch_frequency: 100
        max_images: 1
        increase_log_steps: False

  trainer:
    benchmark: True
    max_steps: 1001