stable-diffusion-webui

1
model:
2
  base_learning_rate: 1.0e-04
3
  target: ldm.models.diffusion.ddpm.LatentDiffusion
4
  params:
5
    linear_start: 0.00085
6
    linear_end: 0.0120
7
    num_timesteps_cond: 1
8
    log_every_t: 200
9
    timesteps: 1000
10
    first_stage_key: "jpg"
11
    cond_stage_key: "txt"
12
    image_size: 64
13
    channels: 4
14
    cond_stage_trainable: false   # Note: different from the one we trained before
15
    conditioning_key: crossattn
16
    monitor: val/loss_simple_ema
17
    scale_factor: 0.18215
18
    use_ema: False
19

20
    scheduler_config: # 10000 warmup steps
21
      target: ldm.lr_scheduler.LambdaLinearScheduler
22
      params:
23
        warm_up_steps: [ 10000 ]
24
        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
25
        f_start: [ 1.e-6 ]
26
        f_max: [ 1. ]
27
        f_min: [ 1. ]
28

29
    unet_config:
30
      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
31
      params:
32
        image_size: 32 # unused
33
        in_channels: 4
34
        out_channels: 4
35
        model_channels: 320
36
        attention_resolutions: [ 4, 2, 1 ]
37
        num_res_blocks: 2
38
        channel_mult: [ 1, 2, 4, 4 ]
39
        num_head_channels: 64
40
        use_spatial_transformer: True
41
        use_linear_in_transformer: True
42
        transformer_depth: 1
43
        context_dim: 1024
44
        use_checkpoint: True
45
        legacy: False
46

47
    first_stage_config:
48
      target: ldm.models.autoencoder.AutoencoderKL
49
      params:
50
        embed_dim: 4
51
        monitor: val/rec_loss
52
        ddconfig:
53
          double_z: true
54
          z_channels: 4
55
          resolution: 256
56
          in_channels: 3
57
          out_ch: 3
58
          ch: 128
59
          ch_mult:
60
          - 1
61
          - 2
62
          - 4
63
          - 4
64
          num_res_blocks: 2
65
          attn_resolutions: []
66
          dropout: 0.0
67
        lossconfig:
68
          target: torch.nn.Identity
69

70
    cond_stage_config:
71
      target: modules.xlmr_m18.BertSeriesModelWithTransformation
72
      params:
73
        name: "XLMR-Large"
74