Reza Shirkavand
commited on
Commit
•
aa8b458
1
Parent(s):
9f7f71c
Add APTP-Small-CC3M
Browse files- APTP-Small-CC3M/arch0/checkpoint-30000/arch_vector.pt +3 -0
- APTP-Small-CC3M/arch0/checkpoint-30000/unet/config.json +74 -0
- APTP-Small-CC3M/arch0/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
- APTP-Small-CC3M/arch1/checkpoint-30000/arch_vector.pt +3 -0
- APTP-Small-CC3M/arch1/checkpoint-30000/unet/config.json +74 -0
- APTP-Small-CC3M/arch1/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
- APTP-Small-CC3M/arch2/checkpoint-30000/arch_vector.pt +3 -0
- APTP-Small-CC3M/arch2/checkpoint-30000/unet/config.json +74 -0
- APTP-Small-CC3M/arch2/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
- APTP-Small-CC3M/arch3/checkpoint-30000/arch_vector.pt +3 -0
- APTP-Small-CC3M/arch3/checkpoint-30000/unet/config.json +74 -0
- APTP-Small-CC3M/arch3/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
- APTP-Small-CC3M/arch4/checkpoint-30000/arch_vector.pt +3 -0
- APTP-Small-CC3M/arch4/checkpoint-30000/unet/config.json +74 -0
- APTP-Small-CC3M/arch4/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
- APTP-Small-CC3M/arch5/checkpoint-30000/arch_vector.pt +3 -0
- APTP-Small-CC3M/arch5/checkpoint-30000/unet/config.json +74 -0
- APTP-Small-CC3M/arch5/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
- APTP-Small-CC3M/arch6/checkpoint-30000/arch_vector.pt +3 -0
- APTP-Small-CC3M/arch6/checkpoint-30000/unet/config.json +74 -0
- APTP-Small-CC3M/arch6/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
- APTP-Small-CC3M/arch7/checkpoint-30000/arch_vector.pt +3 -0
- APTP-Small-CC3M/arch7/checkpoint-30000/unet/config.json +74 -0
- APTP-Small-CC3M/arch7/checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
APTP-Small-CC3M/arch0/checkpoint-30000/arch_vector.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e1b43257629230a948c23f367bf2f51222cc6e10ad3c0fe26d57e360004852f
|
3 |
+
size 53040
|
APTP-Small-CC3M/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-CC3M/arch0/checkpoint-30000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:248ad56075f59e2cea2e7524e727bfdbeda8d5f2433f2e78dcb6b01c331d03f2
|
3 |
+
size 1756687440
|
APTP-Small-CC3M/arch1/checkpoint-30000/arch_vector.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2985843945c5bc7b67b293f1462187048ab3a2245f576ca9970dad4e1cf2240
|
3 |
+
size 53040
|
APTP-Small-CC3M/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-CC3M/arch1/checkpoint-30000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20ffffcbb4d82c66be61356b763ea0cdaebd8607a4652d636c4a4b4f52b61b26
|
3 |
+
size 1772324696
|
APTP-Small-CC3M/arch2/checkpoint-30000/arch_vector.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cf387cde4c9ef36590d41f02bac696d9407ad181c046148d48855486650261b
|
3 |
+
size 53040
|
APTP-Small-CC3M/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-CC3M/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:b1c9b55374644e2b29642ea8cf25341826d884ea910aacebb082fe9fb39f5164
|
3 |
+
size 1692809456
|
APTP-Small-CC3M/arch3/checkpoint-30000/arch_vector.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1aba8bf8531414548b4beb08ac405b20080996f528b4296a1a8689c853bbdae
|
3 |
+
size 53040
|
APTP-Small-CC3M/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-CC3M/arch3/checkpoint-30000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:936dee44112ddbb3c1870cdceafeac57e87f3321a870477e263c9de6154ad652
|
3 |
+
size 1840048896
|
APTP-Small-CC3M/arch4/checkpoint-30000/arch_vector.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2d899c0f331e9e86bbad9dc53bd39cf1e2da146aff8516a19dc22129402fd5d
|
3 |
+
size 53040
|
APTP-Small-CC3M/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-CC3M/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:e0c4d539f2ad7176d21392caaaa29c47f7123c644f48b6cd565ed88c0a1b03d6
|
3 |
+
size 1719537976
|
APTP-Small-CC3M/arch5/checkpoint-30000/arch_vector.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:941bfac2cf9b31f07930094037d44125dd23b48c493960d3b75f65efbd67a641
|
3 |
+
size 53040
|
APTP-Small-CC3M/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-CC3M/arch5/checkpoint-30000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11cd85d42eddf168815292c86a89ae76adfcaef4eb154c2120e7cbdc390e9aa1
|
3 |
+
size 1790728552
|
APTP-Small-CC3M/arch6/checkpoint-30000/arch_vector.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7ac2e9cff7c60170b12af84cdd67829a1ed9a7e10c3e96c2443156385655dbe
|
3 |
+
size 53040
|
APTP-Small-CC3M/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-CC3M/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:ff1a5a000e1ac47eb94f0bad8774dc1b368948634e615d02126f1894ce208e13
|
3 |
+
size 2239311352
|
APTP-Small-CC3M/arch7/checkpoint-30000/arch_vector.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98afdb3cbdfe7dc7151938d45bd662cbafba56978d1ac326cd5a66db4dc7c5a7
|
3 |
+
size 53040
|
APTP-Small-CC3M/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-CC3M/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:c25da3d366e59ab2ac05309c0c37856af9670faff5fd8f75f6dbf816534f23b1
|
3 |
+
size 1770367688
|