English
Japanese
a
Phantom-Artist commited on
Commit
cf8e321
1 Parent(s): 1ac629a

Upload yamls

Browse files
phantom_852wa_style_Diffusion.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"
phantom_aibanousagi_style_Diffusion.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"
phantom_aioeoekakino_style_Diffusion.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"
phantom_airhara_style_Diffusion.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"
phantom_alfredplpl_style_Diffusion.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"
phantom_callimiya_style_Diffusion.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"
phantom_citrus_style_Diffusion.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"
phantom_elessenar_style_Diffusion.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"
phantom_kiri_style_Diffusion.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"
phantom_korocon_style_Diffusion.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"
phantom_lakeside_style_Diffusion.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"
phantom_maccha_style_Diffusion.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"
phantom_natsuku_style_Diffusion.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"
phantom_nikaido_style_Diffusion.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"
phantom_plat_style_Diffusion.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"
phantom_roiyaruRIZ_style_Diffusion.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"
phantom_swingwings_style_Diffusion.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"
phantom_tuinositone_style_Diffusion.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"
phantom_yunyalula_style_Diffusion.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"
phantom_yuyuyu_style_Diffusion.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"