fluffyrock-1088-megares-terminal-snr-vpred/fluffyrock-576-704-832-960-1088-lion-low-lr-e49-terminal-snr-vpred-e22.yaml ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-04
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false # Note: different from the one we trained before
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False
20
+
21
+ scheduler_config: # 10000 warmup steps
22
+ target: ldm.lr_scheduler.LambdaLinearScheduler
23
+ params:
24
+ warm_up_steps: [ 10000 ]
25
+ cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
26
+ f_start: [ 1.e-6 ]
27
+ f_max: [ 1. ]
28
+ f_min: [ 1. ]
29
+
30
+ unet_config:
31
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
32
+ params:
33
+ image_size: 32 # unused
34
+ in_channels: 4
35
+ out_channels: 4
36
+ model_channels: 320
37
+ attention_resolutions: [ 4, 2, 1 ]
38
+ num_res_blocks: 2
39
+ channel_mult: [ 1, 2, 4, 4 ]
40
+ num_heads: 8
41
+ use_spatial_transformer: True
42
+ transformer_depth: 1
43
+ context_dim: 768
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: ldm.modules.encoders.modules.FrozenCLIPEmbedder
fluffyrock-1088-megares-terminal-snr-vpred/fluffyrock-576-704-832-960-1088-lion-low-lr-e51-terminal-snr-vpred-e24.yaml ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-04
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false # Note: different from the one we trained before
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False
20
+
21
+ scheduler_config: # 10000 warmup steps
22
+ target: ldm.lr_scheduler.LambdaLinearScheduler
23
+ params:
24
+ warm_up_steps: [ 10000 ]
25
+ cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
26
+ f_start: [ 1.e-6 ]
27
+ f_max: [ 1. ]
28
+ f_min: [ 1. ]
29
+
30
+ unet_config:
31
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
32
+ params:
33
+ image_size: 32 # unused
34
+ in_channels: 4
35
+ out_channels: 4
36
+ model_channels: 320
37
+ attention_resolutions: [ 4, 2, 1 ]
38
+ num_res_blocks: 2
39
+ channel_mult: [ 1, 2, 4, 4 ]
40
+ num_heads: 8
41
+ use_spatial_transformer: True
42
+ transformer_depth: 1
43
+ context_dim: 768
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: ldm.modules.encoders.modules.FrozenCLIPEmbedder
fluffyrock-1088-megares-terminal-snr-vpred/fluffyrock-576-704-832-960-1088-lion-low-lr-e53-terminal-snr-vpred-e26.yaml ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ parameterization: "v"
20
+
21
+ scheduler_config: # 10000 warmup steps
22
+ target: ldm.lr_scheduler.LambdaLinearScheduler
23
+ params:
24
+ warm_up_steps: [ 10000 ]
25
+ cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
26
+ f_start: [ 1.e-6 ]
27
+ f_max: [ 1. ]
28
+ f_min: [ 1. ]
29
+
30
+ unet_config:
31
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
32
+ params:
33
+ image_size: 32 # unused
34
+ in_channels: 4
35
+ out_channels: 4
36
+ model_channels: 320
37
+ attention_resolutions: [ 4, 2, 1 ]
38
+ num_res_blocks: 2
39
+ channel_mult: [ 1, 2, 4, 4 ]
40
+ num_heads: 8
41
+ use_spatial_transformer: True
42
+ transformer_depth: 1
43
+ context_dim: 768
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: ldm.modules.encoders.modules.FrozenCLIPEmbedder
fluffyrock-1088-megares-terminal-snr-vpred/fluffyrock-576-704-832-960-1088-lion-low-lr-e55-terminal-snr-vpred-e28.yaml ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ parameterization: "v"
20
+
21
+ scheduler_config: # 10000 warmup steps
22
+ target: ldm.lr_scheduler.LambdaLinearScheduler
23
+ params:
24
+ warm_up_steps: [ 10000 ]
25
+ cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
26
+ f_start: [ 1.e-6 ]
27
+ f_max: [ 1. ]
28
+ f_min: [ 1. ]
29
+
30
+ unet_config:
31
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
32
+ params:
33
+ image_size: 32 # unused
34
+ in_channels: 4
35
+ out_channels: 4
36
+ model_channels: 320
37
+ attention_resolutions: [ 4, 2, 1 ]
38
+ num_res_blocks: 2
39
+ channel_mult: [ 1, 2, 4, 4 ]
40
+ num_heads: 8
41
+ use_spatial_transformer: True
42
+ transformer_depth: 1
43
+ context_dim: 768
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: ldm.modules.encoders.modules.FrozenCLIPEmbedder
fluffyrock-1088-megares-terminal-snr-vpred/fluffyrock-576-704-832-960-1088-lion-low-lr-e59-terminal-snr-vpred-e32.yaml ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ parameterization: "v"
20
+
21
+ scheduler_config: # 10000 warmup steps
22
+ target: ldm.lr_scheduler.LambdaLinearScheduler
23
+ params:
24
+ warm_up_steps: [ 10000 ]
25
+ cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
26
+ f_start: [ 1.e-6 ]
27
+ f_max: [ 1. ]
28
+ f_min: [ 1. ]
29
+
30
+ unet_config:
31
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
32
+ params:
33
+ image_size: 32 # unused
34
+ in_channels: 4
35
+ out_channels: 4
36
+ model_channels: 320
37
+ attention_resolutions: [ 4, 2, 1 ]
38
+ num_res_blocks: 2
39
+ channel_mult: [ 1, 2, 4, 4 ]
40
+ num_heads: 8
41
+ use_spatial_transformer: True
42
+ transformer_depth: 1
43
+ context_dim: 768
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: ldm.modules.encoders.modules.FrozenCLIPEmbedder
fluffyrock-1088-megares-terminal-snr-vpred/fluffyrock-576-704-832-960-1088-lion-low-lr-e65-terminal-snr-vpred-e38.yaml ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-04
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false # Note: different from the one we trained before
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False
20
+
21
+ scheduler_config: # 10000 warmup steps
22
+ target: ldm.lr_scheduler.LambdaLinearScheduler
23
+ params:
24
+ warm_up_steps: [ 10000 ]
25
+ cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
26
+ f_start: [ 1.e-6 ]
27
+ f_max: [ 1. ]
28
+ f_min: [ 1. ]
29
+
30
+ unet_config:
31
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
32
+ params:
33
+ image_size: 32 # unused
34
+ in_channels: 4
35
+ out_channels: 4
36
+ model_channels: 320
37
+ attention_resolutions: [ 4, 2, 1 ]
38
+ num_res_blocks: 2
39
+ channel_mult: [ 1, 2, 4, 4 ]
40
+ num_heads: 8
41
+ use_spatial_transformer: True
42
+ transformer_depth: 1
43
+ context_dim: 768
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: ldm.modules.encoders.modules.FrozenCLIPEmbedder
fluffyrock-1088-megares-terminal-snr-vpred/fluffyrock-576-704-832-960-1088-lion-low-lr-e69-terminal-snr-vpred-e42.yaml ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-04
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false # Note: different from the one we trained before
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False
20
+
21
+ scheduler_config: # 10000 warmup steps
22
+ target: ldm.lr_scheduler.LambdaLinearScheduler
23
+ params:
24
+ warm_up_steps: [ 10000 ]
25
+ cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
26
+ f_start: [ 1.e-6 ]
27
+ f_max: [ 1. ]
28
+ f_min: [ 1. ]
29
+
30
+ unet_config:
31
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
32
+ params:
33
+ image_size: 32 # unused
34
+ in_channels: 4
35
+ out_channels: 4
36
+ model_channels: 320
37
+ attention_resolutions: [ 4, 2, 1 ]
38
+ num_res_blocks: 2
39
+ channel_mult: [ 1, 2, 4, 4 ]
40
+ num_heads: 8
41
+ use_spatial_transformer: True
42
+ transformer_depth: 1
43
+ context_dim: 768
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: ldm.modules.encoders.modules.FrozenCLIPEmbedder
fluffyrock-1088-megares-terminal-snr-vpred/fluffyrock-576-704-832-960-1088-lion-low-lr-e75-terminal-snr-vpred-e48.yaml ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-04
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false # Note: different from the one we trained before
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False
20
+
21
+ scheduler_config: # 10000 warmup steps
22
+ target: ldm.lr_scheduler.LambdaLinearScheduler
23
+ params:
24
+ warm_up_steps: [ 10000 ]
25
+ cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
26
+ f_start: [ 1.e-6 ]
27
+ f_max: [ 1. ]
28
+ f_min: [ 1. ]
29
+
30
+ unet_config:
31
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
32
+ params:
33
+ image_size: 32 # unused
34
+ in_channels: 4
35
+ out_channels: 4
36
+ model_channels: 320
37
+ attention_resolutions: [ 4, 2, 1 ]
38
+ num_res_blocks: 2
39
+ channel_mult: [ 1, 2, 4, 4 ]
40
+ num_heads: 8
41
+ use_spatial_transformer: True
42
+ transformer_depth: 1
43
+ context_dim: 768
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: ldm.modules.encoders.modules.FrozenCLIPEmbedder
fluffyrock-1088-megares-terminal-snr-vpred/fluffyrock-576-704-832-960-1088-lion-low-lr-e82-terminal-snr-vpred-e55.yaml ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-04
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false # Note: different from the one we trained before
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False
20
+
21
+ scheduler_config: # 10000 warmup steps
22
+ target: ldm.lr_scheduler.LambdaLinearScheduler
23
+ params:
24
+ warm_up_steps: [ 10000 ]
25
+ cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
26
+ f_start: [ 1.e-6 ]
27
+ f_max: [ 1. ]
28
+ f_min: [ 1. ]
29
+
30
+ unet_config:
31
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
32
+ params:
33
+ image_size: 32 # unused
34
+ in_channels: 4
35
+ out_channels: 4
36
+ model_channels: 320
37
+ attention_resolutions: [ 4, 2, 1 ]
38
+ num_res_blocks: 2
39
+ channel_mult: [ 1, 2, 4, 4 ]
40
+ num_heads: 8
41
+ use_spatial_transformer: True
42
+ transformer_depth: 1
43
+ context_dim: 768
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: ldm.modules.encoders.modules.FrozenCLIPEmbedder