Hugging Face's logo

rezashkv
/
diffusion_pruning

Text-to-Image
Diffusers
Safetensors
English
stable-diffusion
Model card Files Community
Reza Shirkavand commited on
Commit
ab2434b
•
1 Parent(s): aa8b458

add coco models

Browse files
Files changed (48) hide show
  1. APTP-Base-COCO/arch0/checkpoint-30000/arch_vector.pt +3 -0
  2. APTP-Base-COCO/arch0/checkpoint-30000/unet/config.json +74 -0
  3. APTP-Base-COCO/arch0/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  4. APTP-Base-COCO/arch1/checkpoint-30000/arch_vector.pt +3 -0
  5. APTP-Base-COCO/arch1/checkpoint-30000/unet/config.json +74 -0
  6. APTP-Base-COCO/arch1/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  7. APTP-Base-COCO/arch2/checkpoint-30000/arch_vector.pt +3 -0
  8. APTP-Base-COCO/arch2/checkpoint-30000/unet/config.json +74 -0
  9. APTP-Base-COCO/arch2/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  10. APTP-Base-COCO/arch3/checkpoint-30000/arch_vector.pt +3 -0
  11. APTP-Base-COCO/arch3/checkpoint-30000/unet/config.json +74 -0
  12. APTP-Base-COCO/arch3/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  13. APTP-Base-COCO/arch4/checkpoint-30000/arch_vector.pt +3 -0
  14. APTP-Base-COCO/arch4/checkpoint-30000/unet/config.json +74 -0
  15. APTP-Base-COCO/arch4/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  16. APTP-Base-COCO/arch5/checkpoint-30000/arch_vector.pt +3 -0
  17. APTP-Base-COCO/arch5/checkpoint-30000/unet/config.json +74 -0
  18. APTP-Base-COCO/arch5/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  19. APTP-Base-COCO/arch6/checkpoint-30000/arch_vector.pt +3 -0
  20. APTP-Base-COCO/arch6/checkpoint-30000/unet/config.json +74 -0
  21. APTP-Base-COCO/arch6/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  22. APTP-Base-COCO/arch7/checkpoint-30000/arch_vector.pt +3 -0
  23. APTP-Base-COCO/arch7/checkpoint-30000/unet/config.json +74 -0
  24. APTP-Base-COCO/arch7/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  25. APTP-Small-COCO/arch0/checkpoint-30000/arch_vector.pt +3 -0
  26. APTP-Small-COCO/arch0/checkpoint-30000/unet/config.json +74 -0
  27. APTP-Small-COCO/arch0/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  28. APTP-Small-COCO/arch1/checkpoint-30000/arch_vector.pt +3 -0
  29. APTP-Small-COCO/arch1/checkpoint-30000/unet/config.json +74 -0
  30. APTP-Small-COCO/arch1/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  31. APTP-Small-COCO/arch2/checkpoint-30000/arch_vector.pt +3 -0
  32. APTP-Small-COCO/arch2/checkpoint-30000/unet/config.json +74 -0
  33. APTP-Small-COCO/arch2/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  34. APTP-Small-COCO/arch3/checkpoint-30000/arch_vector.pt +3 -0
  35. APTP-Small-COCO/arch3/checkpoint-30000/unet/config.json +74 -0
  36. APTP-Small-COCO/arch3/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  37. APTP-Small-COCO/arch4/checkpoint-30000/arch_vector.pt +3 -0
  38. APTP-Small-COCO/arch4/checkpoint-30000/unet/config.json +74 -0
  39. APTP-Small-COCO/arch4/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  40. APTP-Small-COCO/arch5/checkpoint-30000/arch_vector.pt +3 -0
  41. APTP-Small-COCO/arch5/checkpoint-30000/unet/config.json +74 -0
  42. APTP-Small-COCO/arch5/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  43. APTP-Small-COCO/arch6/checkpoint-30000/arch_vector.pt +3 -0
  44. APTP-Small-COCO/arch6/checkpoint-30000/unet/config.json +74 -0
  45. APTP-Small-COCO/arch6/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
  46. APTP-Small-COCO/arch7/checkpoint-30000/arch_vector.pt +3 -0
  47. APTP-Small-COCO/arch7/checkpoint-30000/unet/config.json +74 -0
  48. APTP-Small-COCO/arch7/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
APTP-Base-COCO/arch0/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ac21db6b257eaf48a4db0e9c418c725d4efc590d7f1cb97d57d43b35b9999ea
3
+ size 53040
APTP-Base-COCO/arch0/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Base-COCO/arch0/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f8fcb6867ca725d978c4d4e85033d7447c3cc95e2b6e096cf25510b98a0b28
3
+ size 2306984384
APTP-Base-COCO/arch1/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f69c11eac6cb5c8ec94f5a520c7a57a39bf2d1c25be58bca20aa264b59ff0ef7
3
+ size 53040
APTP-Base-COCO/arch1/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Base-COCO/arch1/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72162c8efffa3209a4d104ff465f1c756d1944630f3b45fdb2005622f33361bc
3
+ size 2311852024
APTP-Base-COCO/arch2/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f6437fdbe726f38489c8704e14e3832e24a32f3624d679c0d71ed661b0f72d
3
+ size 53040
APTP-Base-COCO/arch2/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Base-COCO/arch2/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed683b10c330c80ef54473401a246fec1eadcdf14e2ef1779d9706ec3f491739
3
+ size 1918058952
APTP-Base-COCO/arch3/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc617e2667de62e4b531c2a28065b333c7083d435d485768b12c9e6faa04667
3
+ size 53040
APTP-Base-COCO/arch3/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Base-COCO/arch3/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f02994529a6b1364568c069b534b1ff6fa14c07007cc50e3c040a42a30d46492
3
+ size 2385036056
APTP-Base-COCO/arch4/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:407cde29ecb84d589e13adcc3ddfd049bdca0196d71470f522cd4ef9d9be0420
3
+ size 53040
APTP-Base-COCO/arch4/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Base-COCO/arch4/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8fb58df0a12fae14d3af02a3f8feec0a24d3bc281f86856c3d68ef84476f205
3
+ size 2375840144
APTP-Base-COCO/arch5/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cda975b7812e5ab006365afe2ff61960f87b1ee41604d26e73e8a8cff842b57e
3
+ size 53040
APTP-Base-COCO/arch5/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Base-COCO/arch5/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be95d0fb26d6e097ed97eb6c232d93d96fb471c74b38b0a31c69374b5a412abe
3
+ size 2690249016
APTP-Base-COCO/arch6/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5898a1f37ed8cdc466189050986c8c0931619f0e7276aa996409e5f2c144a339
3
+ size 53040
APTP-Base-COCO/arch6/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Base-COCO/arch6/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f44d54b11b9a4b22a33cd247c2f7d2bbd312633f3d2e14735eca75a7f6e234
3
+ size 2274483224
APTP-Base-COCO/arch7/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd39e9ad7fba835d27a79f08e5725754b3a3d62df9dbfa11d165e6a6f5d70aae
3
+ size 53040
APTP-Base-COCO/arch7/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Base-COCO/arch7/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3813a9cfb62e656ff3c3c09232179dc7471d51471faee8322eb2a3f6b0ebdc15
3
+ size 2236506112
APTP-Small-COCO/arch0/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a351136e013e4b76926cda88b580bca1bbdb9fa3c1aac0a23238319010a2cb
3
+ size 53040
APTP-Small-COCO/arch0/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Small-COCO/arch0/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b5c529be188d84a72fc68c459ba532094a7de434794ce1af0a8318bf6fe1f40
3
+ size 1739495328
APTP-Small-COCO/arch1/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14fb52aedcc83c59146eab7ec12f394c64d4da1c7ba98626948c123f27e0a5a7
3
+ size 53040
APTP-Small-COCO/arch1/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Small-COCO/arch1/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc180f7208a7351706716f1156616c0c6b1755f9bde4d2a74ba1b228c6b9ac12
3
+ size 1788203224
APTP-Small-COCO/arch2/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91adafef1d1674e84180624ab9664f814148d49aa5b679341f70f709ee200e98
3
+ size 53040
APTP-Small-COCO/arch2/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Small-COCO/arch2/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06eb5e9eed61a662b9463b4840504b142f0afd6018323ccf696cde9f760fb0f7
3
+ size 1936561096
APTP-Small-COCO/arch3/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91633d180f07ede228cd6ab67461e1d9cf6f49f3bc6cd057eb31bf7b9f6fa205
3
+ size 53040
APTP-Small-COCO/arch3/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Small-COCO/arch3/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8da288debbdbf210f7d0dc71d457c99c10af7747f754b28ed55f556d535d2ac
3
+ size 1734064064
APTP-Small-COCO/arch4/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:852d51c2097b82376372db9b7ed3644821d694690fc261868d954e0a941f8cd8
3
+ size 53040
APTP-Small-COCO/arch4/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Small-COCO/arch4/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f27bd880acc73b8b9d5c5d3becb92d957c500aa96a02368cff8d652efe79f83f
3
+ size 1865645360
APTP-Small-COCO/arch5/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b951506ef927590e405cb000431d77592efbc8ce399a920f0a21fbbda0a6c1d
3
+ size 53040
APTP-Small-COCO/arch5/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Small-COCO/arch5/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d90896ec2e32771155541fde942fd3d13a2ed60b4be56e8564ff84d53e5a230f
3
+ size 1880172000
APTP-Small-COCO/arch6/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5543b601c8cbfcbbaf48c63c2f51c6915de303fe680b86a98a3d05b274591f1c
3
+ size 53040
APTP-Small-COCO/arch6/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Small-COCO/arch6/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f36e251647a2ac39b86e830ddd7ee086f54532c8f529cf39474335f5680546
3
+ size 1841496136
APTP-Small-COCO/arch7/checkpoint-30000/arch_vector.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606a0e68efaa05b8f2b8c486cbcd42d642d03e4d5d725a60f74e34f1f687ab43
3
+ size 53040
APTP-Small-COCO/arch7/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModelPruned",
3
+ "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2DHalfGated",
31
+ "CrossAttnDownBlock2DHalfGated",
32
+ "CrossAttnDownBlock2DHalfGated",
33
+ "DownBlock2DHalfGated"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "ff_gate_width": 32,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "gated_ff": true,
44
+ "in_channels": 4,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttnWidthGated",
49
+ "norm_eps": 1e-05,
50
+ "norm_num_groups": 32,
51
+ "num_attention_heads": null,
52
+ "num_class_embeds": null,
53
+ "only_cross_attention": false,
54
+ "out_channels": 4,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "sample_size": 96,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "UpBlock2DHalfGated",
68
+ "CrossAttnUpBlock2DHalfGated",
69
+ "CrossAttnUpBlock2DHalfGated",
70
+ "CrossAttnUpBlock2DHalfGated"
71
+ ],
72
+ "upcast_attention": true,
73
+ "use_linear_projection": true
74
+ }
APTP-Small-COCO/arch7/checkpoint-30000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a4319ac612e20d50b0b87edbc803efd65b3f9e32b2fd165b734cf86d162a03
3
+ size 1896049744