Spaces:
Running
on
Zero
Running
on
Zero
declare-lab-sutd
commited on
Commit
•
3f642ea
1
Parent(s):
a120d23
Add config files
Browse files
configs/.ipynb_checkpoints/diffusion_model_config-checkpoint.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.10.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"attention_head_dim": [
|
6 |
+
5,
|
7 |
+
10,
|
8 |
+
20,
|
9 |
+
20
|
10 |
+
],
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"cross_attention_dim": 1024,
|
19 |
+
"down_block_types": [
|
20 |
+
"CrossAttnDownBlock2D",
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"DownBlock2D"
|
24 |
+
],
|
25 |
+
"downsample_padding": 1,
|
26 |
+
"dual_cross_attention": false,
|
27 |
+
"flip_sin_to_cos": true,
|
28 |
+
"freq_shift": 0,
|
29 |
+
"in_channels": 8,
|
30 |
+
"layers_per_block": 2,
|
31 |
+
"mid_block_scale_factor": 1,
|
32 |
+
"norm_eps": 1e-05,
|
33 |
+
"norm_num_groups": 32,
|
34 |
+
"num_class_embeds": null,
|
35 |
+
"only_cross_attention": false,
|
36 |
+
"out_channels": 8,
|
37 |
+
"sample_size": [32, 2],
|
38 |
+
"up_block_types": [
|
39 |
+
"UpBlock2D",
|
40 |
+
"CrossAttnUpBlock2D",
|
41 |
+
"CrossAttnUpBlock2D",
|
42 |
+
"CrossAttnUpBlock2D"
|
43 |
+
],
|
44 |
+
"use_linear_projection": true,
|
45 |
+
"upcast_attention": true
|
46 |
+
}
|
configs/.ipynb_checkpoints/stable_diffusion_2.1-checkpoint.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.10.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"attention_head_dim": [
|
6 |
+
5,
|
7 |
+
10,
|
8 |
+
20,
|
9 |
+
20
|
10 |
+
],
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"cross_attention_dim": 1024,
|
19 |
+
"down_block_types": [
|
20 |
+
"CrossAttnDownBlock2D",
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"DownBlock2D"
|
24 |
+
],
|
25 |
+
"downsample_padding": 1,
|
26 |
+
"dual_cross_attention": false,
|
27 |
+
"flip_sin_to_cos": true,
|
28 |
+
"freq_shift": 0,
|
29 |
+
"in_channels": 4,
|
30 |
+
"layers_per_block": 2,
|
31 |
+
"mid_block_scale_factor": 1,
|
32 |
+
"norm_eps": 1e-05,
|
33 |
+
"norm_num_groups": 32,
|
34 |
+
"num_class_embeds": null,
|
35 |
+
"only_cross_attention": false,
|
36 |
+
"out_channels": 4,
|
37 |
+
"sample_size": 96,
|
38 |
+
"up_block_types": [
|
39 |
+
"UpBlock2D",
|
40 |
+
"CrossAttnUpBlock2D",
|
41 |
+
"CrossAttnUpBlock2D",
|
42 |
+
"CrossAttnUpBlock2D"
|
43 |
+
],
|
44 |
+
"use_linear_projection": true,
|
45 |
+
"upcast_attention": true
|
46 |
+
}
|
configs/diffusion_model_config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.10.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"attention_head_dim": [
|
6 |
+
5,
|
7 |
+
10,
|
8 |
+
20,
|
9 |
+
20
|
10 |
+
],
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"cross_attention_dim": 1024,
|
19 |
+
"down_block_types": [
|
20 |
+
"CrossAttnDownBlock2D",
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"DownBlock2D"
|
24 |
+
],
|
25 |
+
"downsample_padding": 1,
|
26 |
+
"dual_cross_attention": false,
|
27 |
+
"flip_sin_to_cos": true,
|
28 |
+
"freq_shift": 0,
|
29 |
+
"in_channels": 8,
|
30 |
+
"layers_per_block": 2,
|
31 |
+
"mid_block_scale_factor": 1,
|
32 |
+
"norm_eps": 1e-05,
|
33 |
+
"norm_num_groups": 32,
|
34 |
+
"num_class_embeds": null,
|
35 |
+
"only_cross_attention": false,
|
36 |
+
"out_channels": 8,
|
37 |
+
"sample_size": [32, 2],
|
38 |
+
"up_block_types": [
|
39 |
+
"UpBlock2D",
|
40 |
+
"CrossAttnUpBlock2D",
|
41 |
+
"CrossAttnUpBlock2D",
|
42 |
+
"CrossAttnUpBlock2D"
|
43 |
+
],
|
44 |
+
"use_linear_projection": true,
|
45 |
+
"upcast_attention": true
|
46 |
+
}
|
configs/diffusion_model_xl_config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.10.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"attention_head_dim": [
|
6 |
+
5,
|
7 |
+
10,
|
8 |
+
20,
|
9 |
+
20
|
10 |
+
],
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"cross_attention_dim": 2048,
|
19 |
+
"down_block_types": [
|
20 |
+
"CrossAttnDownBlock2D",
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"DownBlock2D"
|
24 |
+
],
|
25 |
+
"downsample_padding": 1,
|
26 |
+
"dual_cross_attention": false,
|
27 |
+
"flip_sin_to_cos": true,
|
28 |
+
"freq_shift": 0,
|
29 |
+
"in_channels": 8,
|
30 |
+
"layers_per_block": 2,
|
31 |
+
"mid_block_scale_factor": 1,
|
32 |
+
"norm_eps": 1e-05,
|
33 |
+
"norm_num_groups": 32,
|
34 |
+
"num_class_embeds": null,
|
35 |
+
"only_cross_attention": false,
|
36 |
+
"out_channels": 8,
|
37 |
+
"sample_size": [32, 2],
|
38 |
+
"up_block_types": [
|
39 |
+
"UpBlock2D",
|
40 |
+
"CrossAttnUpBlock2D",
|
41 |
+
"CrossAttnUpBlock2D",
|
42 |
+
"CrossAttnUpBlock2D"
|
43 |
+
],
|
44 |
+
"use_linear_projection": true,
|
45 |
+
"upcast_attention": true
|
46 |
+
}
|
configs/stable_diffusion_2.1.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.10.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"attention_head_dim": [
|
6 |
+
5,
|
7 |
+
10,
|
8 |
+
20,
|
9 |
+
20
|
10 |
+
],
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"cross_attention_dim": 1024,
|
19 |
+
"down_block_types": [
|
20 |
+
"CrossAttnDownBlock2D",
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"DownBlock2D"
|
24 |
+
],
|
25 |
+
"downsample_padding": 1,
|
26 |
+
"dual_cross_attention": false,
|
27 |
+
"flip_sin_to_cos": true,
|
28 |
+
"freq_shift": 0,
|
29 |
+
"in_channels": 4,
|
30 |
+
"layers_per_block": 2,
|
31 |
+
"mid_block_scale_factor": 1,
|
32 |
+
"norm_eps": 1e-05,
|
33 |
+
"norm_num_groups": 32,
|
34 |
+
"num_class_embeds": null,
|
35 |
+
"only_cross_attention": false,
|
36 |
+
"out_channels": 4,
|
37 |
+
"sample_size": 96,
|
38 |
+
"up_block_types": [
|
39 |
+
"UpBlock2D",
|
40 |
+
"CrossAttnUpBlock2D",
|
41 |
+
"CrossAttnUpBlock2D",
|
42 |
+
"CrossAttnUpBlock2D"
|
43 |
+
],
|
44 |
+
"use_linear_projection": true,
|
45 |
+
"upcast_attention": true
|
46 |
+
}
|