Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
AUTOMATIC1111
GitHub Repository: AUTOMATIC1111/stable-diffusion-webui
 Path: blob/master/configs/instruct-pix2pix.yaml
2447 views
1
# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).

2
# See more details in LICENSE.

3


4
model:

5
  base_learning_rate: 1.0e-04

6
  target: modules.models.diffusion.ddpm_edit.LatentDiffusion

7
  params:

8
    linear_start: 0.00085

9
    linear_end: 0.0120

10
    num_timesteps_cond: 1

11
    log_every_t: 200

12
    timesteps: 1000

13
    first_stage_key: edited

14
    cond_stage_key: edit

15
    # image_size: 64

16
    # image_size: 32

17
    image_size: 16

18
    channels: 4

19
    cond_stage_trainable: false   # Note: different from the one we trained before

20
    conditioning_key: hybrid

21
    monitor: val/loss_simple_ema

22
    scale_factor: 0.18215

23
    use_ema: false

24


25
    scheduler_config: # 10000 warmup steps

26
      target: ldm.lr_scheduler.LambdaLinearScheduler

27
      params:

28
        warm_up_steps: [ 0 ]

29
        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases

30
        f_start: [ 1.e-6 ]

31
        f_max: [ 1. ]

32
        f_min: [ 1. ]

33


34
    unet_config:

35
      target: ldm.modules.diffusionmodules.openaimodel.UNetModel

36
      params:

37
        image_size: 32 # unused

38
        in_channels: 8

39
        out_channels: 4

40
        model_channels: 320

41
        attention_resolutions: [ 4, 2, 1 ]

42
        num_res_blocks: 2

43
        channel_mult: [ 1, 2, 4, 4 ]

44
        num_heads: 8

45
        use_spatial_transformer: True

46
        transformer_depth: 1

47
        context_dim: 768

48
        use_checkpoint: False

49
        legacy: False

50


51
    first_stage_config:

52
      target: ldm.models.autoencoder.AutoencoderKL

53
      params:

54
        embed_dim: 4

55
        monitor: val/rec_loss

56
        ddconfig:

57
          double_z: true

58
          z_channels: 4

59
          resolution: 256

60
          in_channels: 3

61
          out_ch: 3

62
          ch: 128

63
          ch_mult:

64
          - 1

65
          - 2

66
          - 4

67
          - 4

68
          num_res_blocks: 2

69
          attn_resolutions: []

70
          dropout: 0.0

71
        lossconfig:

72
          target: torch.nn.Identity

73


74
    cond_stage_config:

75
      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder

76


77
data:

78
  target: main.DataModuleFromConfig

79
  params:

80
    batch_size: 128

81
    num_workers: 1

82
    wrap: false

83
    validation:

84
      target: edit_dataset.EditDataset

85
      params:

86
        path: data/clip-filtered-dataset

87
        cache_dir:  data/

88
        cache_name: data_10k

89
        split: val

90
        min_text_sim: 0.2

91
        min_image_sim: 0.75

92
        min_direction_sim: 0.2

93
        max_samples_per_prompt: 1

94
        min_resize_res: 512

95
        max_resize_res: 512

96
        crop_res: 512

97
        output_as_edit: False

98
        real_input: True

99


100