ThePioneer commited on
Commit
59e6146
1 Parent(s): a0a6826

Upload 10 files

Browse files
.gitattributes CHANGED
@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ xy_grid-0000-2930115154-masterpiece,[[:space:]]best[[:space:]]quality,[[:space:]]A[[:space:]]teenage[[:space:]]girl[[:space:]]wearing[[:space:]]a[[:space:]]white[[:space:]]feather[[:space:]]down[[:space:]]jacket,[[:space:]]smile,[[:space:]]in[[:space:]]the[[:space:]]style[[:space:]]of[[:space:]]Kyoto[[:space:]]Animation[[:space:]]in[[:space:]]the[[:space:]]201.png filter=lfs diff=lfs merge=lfs -text
36
+ xy_grid-0001-2930115154-masterpiece,[[:space:]]best[[:space:]]quality,[[:space:]]A[[:space:]]teenage[[:space:]]girl[[:space:]]wearing[[:space:]]a[[:space:]]white[[:space:]]feather[[:space:]]down[[:space:]]jacket,[[:space:]]smile,[[:space:]]in[[:space:]]the[[:space:]]style[[:space:]]of[[:space:]]Kyoto[[:space:]]Animation[[:space:]]in[[:space:]]the[[:space:]]201.png filter=lfs diff=lfs merge=lfs -text
0.65(wd-1-4-anime_e2) + 0.35(v2-1-1).yaml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
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
15
+ conditioning_key: crossattn
16
+ monitor: val/loss_simple_ema
17
+ scale_factor: 0.18215
18
+ use_ema: False # we set this to false because this is an inference only config
19
+
20
+ unet_config:
21
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
22
+ params:
23
+ use_checkpoint: True
24
+ use_fp16: True
25
+ image_size: 32 # unused
26
+ in_channels: 4
27
+ out_channels: 4
28
+ model_channels: 320
29
+ attention_resolutions: [ 4, 2, 1 ]
30
+ num_res_blocks: 2
31
+ channel_mult: [ 1, 2, 4, 4 ]
32
+ num_head_channels: 64 # need to fix for flash-attn
33
+ use_spatial_transformer: True
34
+ use_linear_in_transformer: True
35
+ transformer_depth: 1
36
+ context_dim: 1024
37
+ legacy: False
38
+
39
+ first_stage_config:
40
+ target: ldm.models.autoencoder.AutoencoderKL
41
+ params:
42
+ embed_dim: 4
43
+ monitor: val/rec_loss
44
+ ddconfig:
45
+ #attn_type: "vanilla-xformers"
46
+ double_z: true
47
+ z_channels: 4
48
+ resolution: 256
49
+ in_channels: 3
50
+ out_ch: 3
51
+ ch: 128
52
+ ch_mult:
53
+ - 1
54
+ - 2
55
+ - 4
56
+ - 4
57
+ num_res_blocks: 2
58
+ attn_resolutions: []
59
+ dropout: 0.0
60
+ lossconfig:
61
+ target: torch.nn.Identity
62
+
63
+ cond_stage_config:
64
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
65
+ params:
66
+ freeze: True
67
+ layer: "penultimate"
0.7(wd-1-4-anime_e2) + 0.3(v2-1-1).yaml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
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
15
+ conditioning_key: crossattn
16
+ monitor: val/loss_simple_ema
17
+ scale_factor: 0.18215
18
+ use_ema: False # we set this to false because this is an inference only config
19
+
20
+ unet_config:
21
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
22
+ params:
23
+ use_checkpoint: True
24
+ use_fp16: True
25
+ image_size: 32 # unused
26
+ in_channels: 4
27
+ out_channels: 4
28
+ model_channels: 320
29
+ attention_resolutions: [ 4, 2, 1 ]
30
+ num_res_blocks: 2
31
+ channel_mult: [ 1, 2, 4, 4 ]
32
+ num_head_channels: 64 # need to fix for flash-attn
33
+ use_spatial_transformer: True
34
+ use_linear_in_transformer: True
35
+ transformer_depth: 1
36
+ context_dim: 1024
37
+ legacy: False
38
+
39
+ first_stage_config:
40
+ target: ldm.models.autoencoder.AutoencoderKL
41
+ params:
42
+ embed_dim: 4
43
+ monitor: val/rec_loss
44
+ ddconfig:
45
+ #attn_type: "vanilla-xformers"
46
+ double_z: true
47
+ z_channels: 4
48
+ resolution: 256
49
+ in_channels: 3
50
+ out_ch: 3
51
+ ch: 128
52
+ ch_mult:
53
+ - 1
54
+ - 2
55
+ - 4
56
+ - 4
57
+ num_res_blocks: 2
58
+ attn_resolutions: []
59
+ dropout: 0.0
60
+ lossconfig:
61
+ target: torch.nn.Identity
62
+
63
+ cond_stage_config:
64
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
65
+ params:
66
+ freeze: True
67
+ layer: "penultimate"
0.75(wd-1-4-anime_e2) + 0.25(v2-1-1).yaml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
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
15
+ conditioning_key: crossattn
16
+ monitor: val/loss_simple_ema
17
+ scale_factor: 0.18215
18
+ use_ema: False # we set this to false because this is an inference only config
19
+
20
+ unet_config:
21
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
22
+ params:
23
+ use_checkpoint: True
24
+ use_fp16: True
25
+ image_size: 32 # unused
26
+ in_channels: 4
27
+ out_channels: 4
28
+ model_channels: 320
29
+ attention_resolutions: [ 4, 2, 1 ]
30
+ num_res_blocks: 2
31
+ channel_mult: [ 1, 2, 4, 4 ]
32
+ num_head_channels: 64 # need to fix for flash-attn
33
+ use_spatial_transformer: True
34
+ use_linear_in_transformer: True
35
+ transformer_depth: 1
36
+ context_dim: 1024
37
+ legacy: False
38
+
39
+ first_stage_config:
40
+ target: ldm.models.autoencoder.AutoencoderKL
41
+ params:
42
+ embed_dim: 4
43
+ monitor: val/rec_loss
44
+ ddconfig:
45
+ #attn_type: "vanilla-xformers"
46
+ double_z: true
47
+ z_channels: 4
48
+ resolution: 256
49
+ in_channels: 3
50
+ out_ch: 3
51
+ ch: 128
52
+ ch_mult:
53
+ - 1
54
+ - 2
55
+ - 4
56
+ - 4
57
+ num_res_blocks: 2
58
+ attn_resolutions: []
59
+ dropout: 0.0
60
+ lossconfig:
61
+ target: torch.nn.Identity
62
+
63
+ cond_stage_config:
64
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
65
+ params:
66
+ freeze: True
67
+ layer: "penultimate"
0.8(wd-1-4-anime_e2) + 0.2(v2-1-1).yaml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
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
15
+ conditioning_key: crossattn
16
+ monitor: val/loss_simple_ema
17
+ scale_factor: 0.18215
18
+ use_ema: False # we set this to false because this is an inference only config
19
+
20
+ unet_config:
21
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
22
+ params:
23
+ use_checkpoint: True
24
+ use_fp16: True
25
+ image_size: 32 # unused
26
+ in_channels: 4
27
+ out_channels: 4
28
+ model_channels: 320
29
+ attention_resolutions: [ 4, 2, 1 ]
30
+ num_res_blocks: 2
31
+ channel_mult: [ 1, 2, 4, 4 ]
32
+ num_head_channels: 64 # need to fix for flash-attn
33
+ use_spatial_transformer: True
34
+ use_linear_in_transformer: True
35
+ transformer_depth: 1
36
+ context_dim: 1024
37
+ legacy: False
38
+
39
+ first_stage_config:
40
+ target: ldm.models.autoencoder.AutoencoderKL
41
+ params:
42
+ embed_dim: 4
43
+ monitor: val/rec_loss
44
+ ddconfig:
45
+ #attn_type: "vanilla-xformers"
46
+ double_z: true
47
+ z_channels: 4
48
+ resolution: 256
49
+ in_channels: 3
50
+ out_ch: 3
51
+ ch: 128
52
+ ch_mult:
53
+ - 1
54
+ - 2
55
+ - 4
56
+ - 4
57
+ num_res_blocks: 2
58
+ attn_resolutions: []
59
+ dropout: 0.0
60
+ lossconfig:
61
+ target: torch.nn.Identity
62
+
63
+ cond_stage_config:
64
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
65
+ params:
66
+ freeze: True
67
+ layer: "penultimate"
0.85(wd-1-4-anime_e2) + 0.15(v2-1-1).ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14f0ecad120f1393b131468c5bbbd54b0fe7233d1d3b6811deed0ed38f990cc1
3
+ size 5160262167
0.85(wd-1-4-anime_e2) + 0.15(v2-1-1).yaml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
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
15
+ conditioning_key: crossattn
16
+ monitor: val/loss_simple_ema
17
+ scale_factor: 0.18215
18
+ use_ema: False # we set this to false because this is an inference only config
19
+
20
+ unet_config:
21
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
22
+ params:
23
+ use_checkpoint: True
24
+ use_fp16: True
25
+ image_size: 32 # unused
26
+ in_channels: 4
27
+ out_channels: 4
28
+ model_channels: 320
29
+ attention_resolutions: [ 4, 2, 1 ]
30
+ num_res_blocks: 2
31
+ channel_mult: [ 1, 2, 4, 4 ]
32
+ num_head_channels: 64 # need to fix for flash-attn
33
+ use_spatial_transformer: True
34
+ use_linear_in_transformer: True
35
+ transformer_depth: 1
36
+ context_dim: 1024
37
+ legacy: False
38
+
39
+ first_stage_config:
40
+ target: ldm.models.autoencoder.AutoencoderKL
41
+ params:
42
+ embed_dim: 4
43
+ monitor: val/rec_loss
44
+ ddconfig:
45
+ #attn_type: "vanilla-xformers"
46
+ double_z: true
47
+ z_channels: 4
48
+ resolution: 256
49
+ in_channels: 3
50
+ out_ch: 3
51
+ ch: 128
52
+ ch_mult:
53
+ - 1
54
+ - 2
55
+ - 4
56
+ - 4
57
+ num_res_blocks: 2
58
+ attn_resolutions: []
59
+ dropout: 0.0
60
+ lossconfig:
61
+ target: torch.nn.Identity
62
+
63
+ cond_stage_config:
64
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
65
+ params:
66
+ freeze: True
67
+ layer: "penultimate"
0.9(wd-1-4-anime_e2) + 0.1(v2-1-1).yaml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
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
15
+ conditioning_key: crossattn
16
+ monitor: val/loss_simple_ema
17
+ scale_factor: 0.18215
18
+ use_ema: False # we set this to false because this is an inference only config
19
+
20
+ unet_config:
21
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
22
+ params:
23
+ use_checkpoint: True
24
+ use_fp16: True
25
+ image_size: 32 # unused
26
+ in_channels: 4
27
+ out_channels: 4
28
+ model_channels: 320
29
+ attention_resolutions: [ 4, 2, 1 ]
30
+ num_res_blocks: 2
31
+ channel_mult: [ 1, 2, 4, 4 ]
32
+ num_head_channels: 64 # need to fix for flash-attn
33
+ use_spatial_transformer: True
34
+ use_linear_in_transformer: True
35
+ transformer_depth: 1
36
+ context_dim: 1024
37
+ legacy: False
38
+
39
+ first_stage_config:
40
+ target: ldm.models.autoencoder.AutoencoderKL
41
+ params:
42
+ embed_dim: 4
43
+ monitor: val/rec_loss
44
+ ddconfig:
45
+ #attn_type: "vanilla-xformers"
46
+ double_z: true
47
+ z_channels: 4
48
+ resolution: 256
49
+ in_channels: 3
50
+ out_ch: 3
51
+ ch: 128
52
+ ch_mult:
53
+ - 1
54
+ - 2
55
+ - 4
56
+ - 4
57
+ num_res_blocks: 2
58
+ attn_resolutions: []
59
+ dropout: 0.0
60
+ lossconfig:
61
+ target: torch.nn.Identity
62
+
63
+ cond_stage_config:
64
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
65
+ params:
66
+ freeze: True
67
+ layer: "penultimate"
0.95(wd-1-4-anime_e2) + 0.05(v2-1-1).yaml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
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
15
+ conditioning_key: crossattn
16
+ monitor: val/loss_simple_ema
17
+ scale_factor: 0.18215
18
+ use_ema: False # we set this to false because this is an inference only config
19
+
20
+ unet_config:
21
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
22
+ params:
23
+ use_checkpoint: True
24
+ use_fp16: True
25
+ image_size: 32 # unused
26
+ in_channels: 4
27
+ out_channels: 4
28
+ model_channels: 320
29
+ attention_resolutions: [ 4, 2, 1 ]
30
+ num_res_blocks: 2
31
+ channel_mult: [ 1, 2, 4, 4 ]
32
+ num_head_channels: 64 # need to fix for flash-attn
33
+ use_spatial_transformer: True
34
+ use_linear_in_transformer: True
35
+ transformer_depth: 1
36
+ context_dim: 1024
37
+ legacy: False
38
+
39
+ first_stage_config:
40
+ target: ldm.models.autoencoder.AutoencoderKL
41
+ params:
42
+ embed_dim: 4
43
+ monitor: val/rec_loss
44
+ ddconfig:
45
+ #attn_type: "vanilla-xformers"
46
+ double_z: true
47
+ z_channels: 4
48
+ resolution: 256
49
+ in_channels: 3
50
+ out_ch: 3
51
+ ch: 128
52
+ ch_mult:
53
+ - 1
54
+ - 2
55
+ - 4
56
+ - 4
57
+ num_res_blocks: 2
58
+ attn_resolutions: []
59
+ dropout: 0.0
60
+ lossconfig:
61
+ target: torch.nn.Identity
62
+
63
+ cond_stage_config:
64
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
65
+ params:
66
+ freeze: True
67
+ layer: "penultimate"
xy_grid-0000-2930115154-masterpiece, best quality, A teenage girl wearing a white feather down jacket, smile, in the style of Kyoto Animation in the 201.png ADDED

Git LFS Details

  • SHA256: f608ea1f478e154da6a7ddb97f55ca9f9b9f3712e04bdb9a46e9a9adca8aa3a5
  • Pointer size: 133 Bytes
  • Size of remote file: 21.7 MB
xy_grid-0001-2930115154-masterpiece, best quality, A teenage girl wearing a white feather down jacket, smile, in the style of Kyoto Animation in the 201.png ADDED

Git LFS Details

  • SHA256: c4fac064a48841651c1246d05b93329d85b2661c2f983edd181b0ac2c2c1c135
  • Pointer size: 133 Bytes
  • Size of remote file: 18 MB