Epoch 0
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitignore +2 -0
- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-1000/unet/config.json +60 -0
- checkpoint-1000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-1000/unet_ema/config.json +67 -0
- checkpoint-1000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-1500/optimizer.bin +3 -0
- checkpoint-1500/random_states_0.pkl +3 -0
- checkpoint-1500/scaler.pt +3 -0
- checkpoint-1500/scheduler.bin +3 -0
- checkpoint-1500/unet/config.json +60 -0
- checkpoint-1500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-1500/unet_ema/config.json +67 -0
- checkpoint-1500/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-2000/optimizer.bin +3 -0
- checkpoint-2000/random_states_0.pkl +3 -0
- checkpoint-2000/scaler.pt +3 -0
- checkpoint-2000/scheduler.bin +3 -0
- checkpoint-2000/unet/config.json +60 -0
- checkpoint-2000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-2000/unet_ema/config.json +67 -0
- checkpoint-2000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-2500/optimizer.bin +3 -0
- checkpoint-2500/random_states_0.pkl +3 -0
- checkpoint-2500/scaler.pt +3 -0
- checkpoint-2500/scheduler.bin +3 -0
- checkpoint-2500/unet/config.json +60 -0
- checkpoint-2500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-2500/unet_ema/config.json +67 -0
- checkpoint-2500/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-3000/optimizer.bin +3 -0
- checkpoint-3000/random_states_0.pkl +3 -0
- checkpoint-3000/scaler.pt +3 -0
- checkpoint-3000/scheduler.bin +3 -0
- checkpoint-3000/unet/config.json +60 -0
- checkpoint-3000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-3000/unet_ema/config.json +67 -0
- checkpoint-3000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-3500/optimizer.bin +3 -0
- checkpoint-3500/random_states_0.pkl +3 -0
- checkpoint-3500/scaler.pt +3 -0
- checkpoint-3500/scheduler.bin +3 -0
- checkpoint-3500/unet/config.json +60 -0
- checkpoint-3500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-3500/unet_ema/config.json +67 -0
- checkpoint-3500/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-4000/optimizer.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
step_*
|
2 |
+
epoch_*
|
checkpoint-1000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78e012a225fdb7bbb6fd1738c858532b0f77a97c44627f974ab091b86124f2fc
|
3 |
+
size 126008021
|
checkpoint-1000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83fa2f67e0f753105fef47d73fc5232e41b1b3b5c8cc15b7935c99a764bc132a
|
3 |
+
size 14727
|
checkpoint-1000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5366b7320d61a06093b24be283a99cea6076a54f7f6ba1a6b51b8a39f4e8072
|
3 |
+
size 557
|
checkpoint-1000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5183e62fca9410cf8c064c7cfa2a4e2441bd492109284a18943921fd581f1f73
|
3 |
+
size 563
|
checkpoint-1000/unet/config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.16.1",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": 8,
|
8 |
+
"block_out_channels": [
|
9 |
+
128,
|
10 |
+
128,
|
11 |
+
128,
|
12 |
+
128
|
13 |
+
],
|
14 |
+
"center_input_sample": false,
|
15 |
+
"class_embed_type": null,
|
16 |
+
"class_embeddings_concat": false,
|
17 |
+
"conv_in_kernel": 3,
|
18 |
+
"conv_out_kernel": 3,
|
19 |
+
"cross_attention_dim": 256,
|
20 |
+
"cross_attention_norm": null,
|
21 |
+
"down_block_types": [
|
22 |
+
"DownBlock2D",
|
23 |
+
"CrossAttnDownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"DownBlock2D"
|
26 |
+
],
|
27 |
+
"downsample_padding": 1,
|
28 |
+
"dual_cross_attention": false,
|
29 |
+
"encoder_hid_dim": null,
|
30 |
+
"flip_sin_to_cos": true,
|
31 |
+
"freq_shift": 0,
|
32 |
+
"in_channels": 3,
|
33 |
+
"layers_per_block": 2,
|
34 |
+
"mid_block_only_cross_attention": null,
|
35 |
+
"mid_block_scale_factor": 1,
|
36 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
37 |
+
"norm_eps": 1e-05,
|
38 |
+
"norm_num_groups": 32,
|
39 |
+
"num_class_embeds": null,
|
40 |
+
"only_cross_attention": false,
|
41 |
+
"out_channels": 3,
|
42 |
+
"projection_class_embeddings_input_dim": null,
|
43 |
+
"resnet_out_scale_factor": 1.0,
|
44 |
+
"resnet_skip_time_act": false,
|
45 |
+
"resnet_time_scale_shift": "default",
|
46 |
+
"sample_size": 256,
|
47 |
+
"time_cond_proj_dim": null,
|
48 |
+
"time_embedding_act_fn": null,
|
49 |
+
"time_embedding_dim": null,
|
50 |
+
"time_embedding_type": "positional",
|
51 |
+
"timestep_post_act": null,
|
52 |
+
"up_block_types": [
|
53 |
+
"UpBlock2D",
|
54 |
+
"CrossAttnUpBlock2D",
|
55 |
+
"CrossAttnUpBlock2D",
|
56 |
+
"UpBlock2D"
|
57 |
+
],
|
58 |
+
"upcast_attention": false,
|
59 |
+
"use_linear_projection": false
|
60 |
+
}
|
checkpoint-1000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:075bb394aac291cbf62aab6b93a00912b0467b4dc5955e32243f3e927f60e86b
|
3 |
+
size 63003985
|
checkpoint-1000/unet_ema/config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.16.1",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": 8,
|
8 |
+
"block_out_channels": [
|
9 |
+
128,
|
10 |
+
128,
|
11 |
+
128,
|
12 |
+
128
|
13 |
+
],
|
14 |
+
"center_input_sample": false,
|
15 |
+
"class_embed_type": null,
|
16 |
+
"class_embeddings_concat": false,
|
17 |
+
"conv_in_kernel": 3,
|
18 |
+
"conv_out_kernel": 3,
|
19 |
+
"cross_attention_dim": 256,
|
20 |
+
"cross_attention_norm": null,
|
21 |
+
"decay": 0.9999,
|
22 |
+
"down_block_types": [
|
23 |
+
"DownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"DownBlock2D"
|
27 |
+
],
|
28 |
+
"downsample_padding": 1,
|
29 |
+
"dual_cross_attention": false,
|
30 |
+
"encoder_hid_dim": null,
|
31 |
+
"flip_sin_to_cos": true,
|
32 |
+
"freq_shift": 0,
|
33 |
+
"in_channels": 3,
|
34 |
+
"inv_gamma": 1.0,
|
35 |
+
"layers_per_block": 2,
|
36 |
+
"mid_block_only_cross_attention": null,
|
37 |
+
"mid_block_scale_factor": 1,
|
38 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
39 |
+
"min_decay": 0.0,
|
40 |
+
"norm_eps": 1e-05,
|
41 |
+
"norm_num_groups": 32,
|
42 |
+
"num_class_embeds": null,
|
43 |
+
"only_cross_attention": false,
|
44 |
+
"optimization_step": 1000,
|
45 |
+
"out_channels": 3,
|
46 |
+
"power": 0.75,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 256,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"up_block_types": [
|
58 |
+
"UpBlock2D",
|
59 |
+
"CrossAttnUpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"UpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"update_after_step": 0,
|
65 |
+
"use_ema_warmup": true,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
checkpoint-1000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:990263e0b3d432f940a6435ee6ce90ca3fdf95e675c883ca6a9bd74b5bf158c5
|
3 |
+
size 62996305
|
checkpoint-1500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9dcbd695fd72938f007b25f66b904cbe035a5dcc51d4db6925125b9b183f7037
|
3 |
+
size 126008021
|
checkpoint-1500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37da071d228a363bc16534701bdc8d9dfb7c59a7f6b5fe03efd311c90aa586c8
|
3 |
+
size 14727
|
checkpoint-1500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ff8390f6078d6ef41fa2b66a9261e9d63f8d86344bf5b5aada2356ea53dcbc8
|
3 |
+
size 557
|
checkpoint-1500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a02accdf6d213f4ea95c22806d0bef9fd3937bbd2da60d5a21dfbd8731ae1934
|
3 |
+
size 563
|
checkpoint-1500/unet/config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.16.1",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": 8,
|
8 |
+
"block_out_channels": [
|
9 |
+
128,
|
10 |
+
128,
|
11 |
+
128,
|
12 |
+
128
|
13 |
+
],
|
14 |
+
"center_input_sample": false,
|
15 |
+
"class_embed_type": null,
|
16 |
+
"class_embeddings_concat": false,
|
17 |
+
"conv_in_kernel": 3,
|
18 |
+
"conv_out_kernel": 3,
|
19 |
+
"cross_attention_dim": 256,
|
20 |
+
"cross_attention_norm": null,
|
21 |
+
"down_block_types": [
|
22 |
+
"DownBlock2D",
|
23 |
+
"CrossAttnDownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"DownBlock2D"
|
26 |
+
],
|
27 |
+
"downsample_padding": 1,
|
28 |
+
"dual_cross_attention": false,
|
29 |
+
"encoder_hid_dim": null,
|
30 |
+
"flip_sin_to_cos": true,
|
31 |
+
"freq_shift": 0,
|
32 |
+
"in_channels": 3,
|
33 |
+
"layers_per_block": 2,
|
34 |
+
"mid_block_only_cross_attention": null,
|
35 |
+
"mid_block_scale_factor": 1,
|
36 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
37 |
+
"norm_eps": 1e-05,
|
38 |
+
"norm_num_groups": 32,
|
39 |
+
"num_class_embeds": null,
|
40 |
+
"only_cross_attention": false,
|
41 |
+
"out_channels": 3,
|
42 |
+
"projection_class_embeddings_input_dim": null,
|
43 |
+
"resnet_out_scale_factor": 1.0,
|
44 |
+
"resnet_skip_time_act": false,
|
45 |
+
"resnet_time_scale_shift": "default",
|
46 |
+
"sample_size": 256,
|
47 |
+
"time_cond_proj_dim": null,
|
48 |
+
"time_embedding_act_fn": null,
|
49 |
+
"time_embedding_dim": null,
|
50 |
+
"time_embedding_type": "positional",
|
51 |
+
"timestep_post_act": null,
|
52 |
+
"up_block_types": [
|
53 |
+
"UpBlock2D",
|
54 |
+
"CrossAttnUpBlock2D",
|
55 |
+
"CrossAttnUpBlock2D",
|
56 |
+
"UpBlock2D"
|
57 |
+
],
|
58 |
+
"upcast_attention": false,
|
59 |
+
"use_linear_projection": false
|
60 |
+
}
|
checkpoint-1500/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e62e474797cf63048421673504a6c0b5d61abfc97d526e32a3d6b7a2a09204c1
|
3 |
+
size 63003985
|
checkpoint-1500/unet_ema/config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.16.1",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": 8,
|
8 |
+
"block_out_channels": [
|
9 |
+
128,
|
10 |
+
128,
|
11 |
+
128,
|
12 |
+
128
|
13 |
+
],
|
14 |
+
"center_input_sample": false,
|
15 |
+
"class_embed_type": null,
|
16 |
+
"class_embeddings_concat": false,
|
17 |
+
"conv_in_kernel": 3,
|
18 |
+
"conv_out_kernel": 3,
|
19 |
+
"cross_attention_dim": 256,
|
20 |
+
"cross_attention_norm": null,
|
21 |
+
"decay": 0.9999,
|
22 |
+
"down_block_types": [
|
23 |
+
"DownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"DownBlock2D"
|
27 |
+
],
|
28 |
+
"downsample_padding": 1,
|
29 |
+
"dual_cross_attention": false,
|
30 |
+
"encoder_hid_dim": null,
|
31 |
+
"flip_sin_to_cos": true,
|
32 |
+
"freq_shift": 0,
|
33 |
+
"in_channels": 3,
|
34 |
+
"inv_gamma": 1.0,
|
35 |
+
"layers_per_block": 2,
|
36 |
+
"mid_block_only_cross_attention": null,
|
37 |
+
"mid_block_scale_factor": 1,
|
38 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
39 |
+
"min_decay": 0.0,
|
40 |
+
"norm_eps": 1e-05,
|
41 |
+
"norm_num_groups": 32,
|
42 |
+
"num_class_embeds": null,
|
43 |
+
"only_cross_attention": false,
|
44 |
+
"optimization_step": 1500,
|
45 |
+
"out_channels": 3,
|
46 |
+
"power": 0.75,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 256,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"up_block_types": [
|
58 |
+
"UpBlock2D",
|
59 |
+
"CrossAttnUpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"UpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"update_after_step": 0,
|
65 |
+
"use_ema_warmup": true,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
checkpoint-1500/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0400f7509aa5f946cb905026e88bb71a90ac200aa1bf0a78130d8d5182687c73
|
3 |
+
size 62996305
|
checkpoint-2000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcdb6fb77252dda7338617dd99325f332c85a7defd6da9cf0081f8e9950f23dc
|
3 |
+
size 126008021
|
checkpoint-2000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa98c4e894b0762b64b5c04b4610d2f224d91fb74e7656c9a6ea411007c6de5b
|
3 |
+
size 14727
|
checkpoint-2000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75ac69a87a814d58ff9f0cf27cf7816fdf0fcfe75d0a63bdf4e7f7aebdc30366
|
3 |
+
size 557
|
checkpoint-2000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f02e8e7dc26b6b9851badcea75c19840317c7f0d1a968a090d3969c6b851511
|
3 |
+
size 563
|
checkpoint-2000/unet/config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.16.1",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": 8,
|
8 |
+
"block_out_channels": [
|
9 |
+
128,
|
10 |
+
128,
|
11 |
+
128,
|
12 |
+
128
|
13 |
+
],
|
14 |
+
"center_input_sample": false,
|
15 |
+
"class_embed_type": null,
|
16 |
+
"class_embeddings_concat": false,
|
17 |
+
"conv_in_kernel": 3,
|
18 |
+
"conv_out_kernel": 3,
|
19 |
+
"cross_attention_dim": 256,
|
20 |
+
"cross_attention_norm": null,
|
21 |
+
"down_block_types": [
|
22 |
+
"DownBlock2D",
|
23 |
+
"CrossAttnDownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"DownBlock2D"
|
26 |
+
],
|
27 |
+
"downsample_padding": 1,
|
28 |
+
"dual_cross_attention": false,
|
29 |
+
"encoder_hid_dim": null,
|
30 |
+
"flip_sin_to_cos": true,
|
31 |
+
"freq_shift": 0,
|
32 |
+
"in_channels": 3,
|
33 |
+
"layers_per_block": 2,
|
34 |
+
"mid_block_only_cross_attention": null,
|
35 |
+
"mid_block_scale_factor": 1,
|
36 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
37 |
+
"norm_eps": 1e-05,
|
38 |
+
"norm_num_groups": 32,
|
39 |
+
"num_class_embeds": null,
|
40 |
+
"only_cross_attention": false,
|
41 |
+
"out_channels": 3,
|
42 |
+
"projection_class_embeddings_input_dim": null,
|
43 |
+
"resnet_out_scale_factor": 1.0,
|
44 |
+
"resnet_skip_time_act": false,
|
45 |
+
"resnet_time_scale_shift": "default",
|
46 |
+
"sample_size": 256,
|
47 |
+
"time_cond_proj_dim": null,
|
48 |
+
"time_embedding_act_fn": null,
|
49 |
+
"time_embedding_dim": null,
|
50 |
+
"time_embedding_type": "positional",
|
51 |
+
"timestep_post_act": null,
|
52 |
+
"up_block_types": [
|
53 |
+
"UpBlock2D",
|
54 |
+
"CrossAttnUpBlock2D",
|
55 |
+
"CrossAttnUpBlock2D",
|
56 |
+
"UpBlock2D"
|
57 |
+
],
|
58 |
+
"upcast_attention": false,
|
59 |
+
"use_linear_projection": false
|
60 |
+
}
|
checkpoint-2000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:377ab83c786e40af97e64a6e71550a6e96a3ea1515c46876084426d417e23cfb
|
3 |
+
size 63003985
|
checkpoint-2000/unet_ema/config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.16.1",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": 8,
|
8 |
+
"block_out_channels": [
|
9 |
+
128,
|
10 |
+
128,
|
11 |
+
128,
|
12 |
+
128
|
13 |
+
],
|
14 |
+
"center_input_sample": false,
|
15 |
+
"class_embed_type": null,
|
16 |
+
"class_embeddings_concat": false,
|
17 |
+
"conv_in_kernel": 3,
|
18 |
+
"conv_out_kernel": 3,
|
19 |
+
"cross_attention_dim": 256,
|
20 |
+
"cross_attention_norm": null,
|
21 |
+
"decay": 0.9999,
|
22 |
+
"down_block_types": [
|
23 |
+
"DownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"DownBlock2D"
|
27 |
+
],
|
28 |
+
"downsample_padding": 1,
|
29 |
+
"dual_cross_attention": false,
|
30 |
+
"encoder_hid_dim": null,
|
31 |
+
"flip_sin_to_cos": true,
|
32 |
+
"freq_shift": 0,
|
33 |
+
"in_channels": 3,
|
34 |
+
"inv_gamma": 1.0,
|
35 |
+
"layers_per_block": 2,
|
36 |
+
"mid_block_only_cross_attention": null,
|
37 |
+
"mid_block_scale_factor": 1,
|
38 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
39 |
+
"min_decay": 0.0,
|
40 |
+
"norm_eps": 1e-05,
|
41 |
+
"norm_num_groups": 32,
|
42 |
+
"num_class_embeds": null,
|
43 |
+
"only_cross_attention": false,
|
44 |
+
"optimization_step": 2000,
|
45 |
+
"out_channels": 3,
|
46 |
+
"power": 0.75,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 256,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"up_block_types": [
|
58 |
+
"UpBlock2D",
|
59 |
+
"CrossAttnUpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"UpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"update_after_step": 0,
|
65 |
+
"use_ema_warmup": true,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
checkpoint-2000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38559e0ece075ad4f19e5b3d459dd46d9a8ed93540fc0e16d5767992f7d9d47a
|
3 |
+
size 62996305
|
checkpoint-2500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec20757039a9e8494916209c37df8bb50d7d9def1c0d1fbedb18bc1f0fad238f
|
3 |
+
size 126008021
|
checkpoint-2500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9e55618366b38a97f33a0a9d9c1a43f757b2349db06527cfca8e1e871a224eb
|
3 |
+
size 14727
|
checkpoint-2500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bd0a4c0a60bb7c85a507bfd0c04bee951631898886bd56e1a986fee16172322
|
3 |
+
size 557
|
checkpoint-2500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f70c32d68aaecacc708a6a5bd9aa98ab28ac109f205822dde2eff0315e79580a
|
3 |
+
size 563
|
checkpoint-2500/unet/config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.16.1",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": 8,
|
8 |
+
"block_out_channels": [
|
9 |
+
128,
|
10 |
+
128,
|
11 |
+
128,
|
12 |
+
128
|
13 |
+
],
|
14 |
+
"center_input_sample": false,
|
15 |
+
"class_embed_type": null,
|
16 |
+
"class_embeddings_concat": false,
|
17 |
+
"conv_in_kernel": 3,
|
18 |
+
"conv_out_kernel": 3,
|
19 |
+
"cross_attention_dim": 256,
|
20 |
+
"cross_attention_norm": null,
|
21 |
+
"down_block_types": [
|
22 |
+
"DownBlock2D",
|
23 |
+
"CrossAttnDownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"DownBlock2D"
|
26 |
+
],
|
27 |
+
"downsample_padding": 1,
|
28 |
+
"dual_cross_attention": false,
|
29 |
+
"encoder_hid_dim": null,
|
30 |
+
"flip_sin_to_cos": true,
|
31 |
+
"freq_shift": 0,
|
32 |
+
"in_channels": 3,
|
33 |
+
"layers_per_block": 2,
|
34 |
+
"mid_block_only_cross_attention": null,
|
35 |
+
"mid_block_scale_factor": 1,
|
36 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
37 |
+
"norm_eps": 1e-05,
|
38 |
+
"norm_num_groups": 32,
|
39 |
+
"num_class_embeds": null,
|
40 |
+
"only_cross_attention": false,
|
41 |
+
"out_channels": 3,
|
42 |
+
"projection_class_embeddings_input_dim": null,
|
43 |
+
"resnet_out_scale_factor": 1.0,
|
44 |
+
"resnet_skip_time_act": false,
|
45 |
+
"resnet_time_scale_shift": "default",
|
46 |
+
"sample_size": 256,
|
47 |
+
"time_cond_proj_dim": null,
|
48 |
+
"time_embedding_act_fn": null,
|
49 |
+
"time_embedding_dim": null,
|
50 |
+
"time_embedding_type": "positional",
|
51 |
+
"timestep_post_act": null,
|
52 |
+
"up_block_types": [
|
53 |
+
"UpBlock2D",
|
54 |
+
"CrossAttnUpBlock2D",
|
55 |
+
"CrossAttnUpBlock2D",
|
56 |
+
"UpBlock2D"
|
57 |
+
],
|
58 |
+
"upcast_attention": false,
|
59 |
+
"use_linear_projection": false
|
60 |
+
}
|
checkpoint-2500/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fce72e7e48b88d4077fea21e1bc2cd1481425bef6e32b7b5d5b2f7b2fc128da6
|
3 |
+
size 63003985
|
checkpoint-2500/unet_ema/config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.16.1",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": 8,
|
8 |
+
"block_out_channels": [
|
9 |
+
128,
|
10 |
+
128,
|
11 |
+
128,
|
12 |
+
128
|
13 |
+
],
|
14 |
+
"center_input_sample": false,
|
15 |
+
"class_embed_type": null,
|
16 |
+
"class_embeddings_concat": false,
|
17 |
+
"conv_in_kernel": 3,
|
18 |
+
"conv_out_kernel": 3,
|
19 |
+
"cross_attention_dim": 256,
|
20 |
+
"cross_attention_norm": null,
|
21 |
+
"decay": 0.9999,
|
22 |
+
"down_block_types": [
|
23 |
+
"DownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"DownBlock2D"
|
27 |
+
],
|
28 |
+
"downsample_padding": 1,
|
29 |
+
"dual_cross_attention": false,
|
30 |
+
"encoder_hid_dim": null,
|
31 |
+
"flip_sin_to_cos": true,
|
32 |
+
"freq_shift": 0,
|
33 |
+
"in_channels": 3,
|
34 |
+
"inv_gamma": 1.0,
|
35 |
+
"layers_per_block": 2,
|
36 |
+
"mid_block_only_cross_attention": null,
|
37 |
+
"mid_block_scale_factor": 1,
|
38 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
39 |
+
"min_decay": 0.0,
|
40 |
+
"norm_eps": 1e-05,
|
41 |
+
"norm_num_groups": 32,
|
42 |
+
"num_class_embeds": null,
|
43 |
+
"only_cross_attention": false,
|
44 |
+
"optimization_step": 2500,
|
45 |
+
"out_channels": 3,
|
46 |
+
"power": 0.75,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 256,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"up_block_types": [
|
58 |
+
"UpBlock2D",
|
59 |
+
"CrossAttnUpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"UpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"update_after_step": 0,
|
65 |
+
"use_ema_warmup": true,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
checkpoint-2500/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95d719e8b338d792e0aa20943eb6db8d8d9204e469c83f9ddd6d0c766aa0d206
|
3 |
+
size 62996305
|
checkpoint-3000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39eb8acc87e7095d5f686cbdd507b0a79b5c680046efeb2f4d53941ee45d3c6b
|
3 |
+
size 126008021
|
checkpoint-3000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32d08c1ee2aa4a7e84754ac1f02843346364fa999bac9972921e63f025081b76
|
3 |
+
size 14727
|
checkpoint-3000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:934a5681064276d6f72374c4876272ca04c62ca58757f934cc86fe7c97957695
|
3 |
+
size 557
|
checkpoint-3000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6d669e882f9885264f82424b9558427d1271b28e62ae2b678c5cd01998974f2
|
3 |
+
size 563
|
checkpoint-3000/unet/config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.16.1",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": 8,
|
8 |
+
"block_out_channels": [
|
9 |
+
128,
|
10 |
+
128,
|
11 |
+
128,
|
12 |
+
128
|
13 |
+
],
|
14 |
+
"center_input_sample": false,
|
15 |
+
"class_embed_type": null,
|
16 |
+
"class_embeddings_concat": false,
|
17 |
+
"conv_in_kernel": 3,
|
18 |
+
"conv_out_kernel": 3,
|
19 |
+
"cross_attention_dim": 256,
|
20 |
+
"cross_attention_norm": null,
|
21 |
+
"down_block_types": [
|
22 |
+
"DownBlock2D",
|
23 |
+
"CrossAttnDownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"DownBlock2D"
|
26 |
+
],
|
27 |
+
"downsample_padding": 1,
|
28 |
+
"dual_cross_attention": false,
|
29 |
+
"encoder_hid_dim": null,
|
30 |
+
"flip_sin_to_cos": true,
|
31 |
+
"freq_shift": 0,
|
32 |
+
"in_channels": 3,
|
33 |
+
"layers_per_block": 2,
|
34 |
+
"mid_block_only_cross_attention": null,
|
35 |
+
"mid_block_scale_factor": 1,
|
36 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
37 |
+
"norm_eps": 1e-05,
|
38 |
+
"norm_num_groups": 32,
|
39 |
+
"num_class_embeds": null,
|
40 |
+
"only_cross_attention": false,
|
41 |
+
"out_channels": 3,
|
42 |
+
"projection_class_embeddings_input_dim": null,
|
43 |
+
"resnet_out_scale_factor": 1.0,
|
44 |
+
"resnet_skip_time_act": false,
|
45 |
+
"resnet_time_scale_shift": "default",
|
46 |
+
"sample_size": 256,
|
47 |
+
"time_cond_proj_dim": null,
|
48 |
+
"time_embedding_act_fn": null,
|
49 |
+
"time_embedding_dim": null,
|
50 |
+
"time_embedding_type": "positional",
|
51 |
+
"timestep_post_act": null,
|
52 |
+
"up_block_types": [
|
53 |
+
"UpBlock2D",
|
54 |
+
"CrossAttnUpBlock2D",
|
55 |
+
"CrossAttnUpBlock2D",
|
56 |
+
"UpBlock2D"
|
57 |
+
],
|
58 |
+
"upcast_attention": false,
|
59 |
+
"use_linear_projection": false
|
60 |
+
}
|
checkpoint-3000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30bd52e3c4b9c9511e60450093623c5b53c075f6e583012068ee7aa470658ffc
|
3 |
+
size 63003985
|
checkpoint-3000/unet_ema/config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.16.1",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": 8,
|
8 |
+
"block_out_channels": [
|
9 |
+
128,
|
10 |
+
128,
|
11 |
+
128,
|
12 |
+
128
|
13 |
+
],
|
14 |
+
"center_input_sample": false,
|
15 |
+
"class_embed_type": null,
|
16 |
+
"class_embeddings_concat": false,
|
17 |
+
"conv_in_kernel": 3,
|
18 |
+
"conv_out_kernel": 3,
|
19 |
+
"cross_attention_dim": 256,
|
20 |
+
"cross_attention_norm": null,
|
21 |
+
"decay": 0.9999,
|
22 |
+
"down_block_types": [
|
23 |
+
"DownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"DownBlock2D"
|
27 |
+
],
|
28 |
+
"downsample_padding": 1,
|
29 |
+
"dual_cross_attention": false,
|
30 |
+
"encoder_hid_dim": null,
|
31 |
+
"flip_sin_to_cos": true,
|
32 |
+
"freq_shift": 0,
|
33 |
+
"in_channels": 3,
|
34 |
+
"inv_gamma": 1.0,
|
35 |
+
"layers_per_block": 2,
|
36 |
+
"mid_block_only_cross_attention": null,
|
37 |
+
"mid_block_scale_factor": 1,
|
38 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
39 |
+
"min_decay": 0.0,
|
40 |
+
"norm_eps": 1e-05,
|
41 |
+
"norm_num_groups": 32,
|
42 |
+
"num_class_embeds": null,
|
43 |
+
"only_cross_attention": false,
|
44 |
+
"optimization_step": 3000,
|
45 |
+
"out_channels": 3,
|
46 |
+
"power": 0.75,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 256,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"up_block_types": [
|
58 |
+
"UpBlock2D",
|
59 |
+
"CrossAttnUpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"UpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"update_after_step": 0,
|
65 |
+
"use_ema_warmup": true,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
checkpoint-3000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b5e5cda878ee30095660705395693d6058fce16961fef43a5c15e246cea0f33
|
3 |
+
size 62996305
|
checkpoint-3500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fc5d828e027676ec0f835ea1c9154bc1010f8a4a028cafd10f58a95632fa216
|
3 |
+
size 126008021
|
checkpoint-3500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:579a8a8f58c504357fbf5c73d6d79a21da4e8ebbef0c00e49e1ffc88ecdb9f0d
|
3 |
+
size 14727
|
checkpoint-3500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a99b22e9bfee524f6a5caab30a959a71c3f356c7c8ddd54664b8cdf1e1d5a69
|
3 |
+
size 557
|
checkpoint-3500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9459b2f98ea685d02f1f97f85fa40e02fdd398e68167ef414537a01c8f23e8ed
|
3 |
+
size 563
|
checkpoint-3500/unet/config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.16.1",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": 8,
|
8 |
+
"block_out_channels": [
|
9 |
+
128,
|
10 |
+
128,
|
11 |
+
128,
|
12 |
+
128
|
13 |
+
],
|
14 |
+
"center_input_sample": false,
|
15 |
+
"class_embed_type": null,
|
16 |
+
"class_embeddings_concat": false,
|
17 |
+
"conv_in_kernel": 3,
|
18 |
+
"conv_out_kernel": 3,
|
19 |
+
"cross_attention_dim": 256,
|
20 |
+
"cross_attention_norm": null,
|
21 |
+
"down_block_types": [
|
22 |
+
"DownBlock2D",
|
23 |
+
"CrossAttnDownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"DownBlock2D"
|
26 |
+
],
|
27 |
+
"downsample_padding": 1,
|
28 |
+
"dual_cross_attention": false,
|
29 |
+
"encoder_hid_dim": null,
|
30 |
+
"flip_sin_to_cos": true,
|
31 |
+
"freq_shift": 0,
|
32 |
+
"in_channels": 3,
|
33 |
+
"layers_per_block": 2,
|
34 |
+
"mid_block_only_cross_attention": null,
|
35 |
+
"mid_block_scale_factor": 1,
|
36 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
37 |
+
"norm_eps": 1e-05,
|
38 |
+
"norm_num_groups": 32,
|
39 |
+
"num_class_embeds": null,
|
40 |
+
"only_cross_attention": false,
|
41 |
+
"out_channels": 3,
|
42 |
+
"projection_class_embeddings_input_dim": null,
|
43 |
+
"resnet_out_scale_factor": 1.0,
|
44 |
+
"resnet_skip_time_act": false,
|
45 |
+
"resnet_time_scale_shift": "default",
|
46 |
+
"sample_size": 256,
|
47 |
+
"time_cond_proj_dim": null,
|
48 |
+
"time_embedding_act_fn": null,
|
49 |
+
"time_embedding_dim": null,
|
50 |
+
"time_embedding_type": "positional",
|
51 |
+
"timestep_post_act": null,
|
52 |
+
"up_block_types": [
|
53 |
+
"UpBlock2D",
|
54 |
+
"CrossAttnUpBlock2D",
|
55 |
+
"CrossAttnUpBlock2D",
|
56 |
+
"UpBlock2D"
|
57 |
+
],
|
58 |
+
"upcast_attention": false,
|
59 |
+
"use_linear_projection": false
|
60 |
+
}
|
checkpoint-3500/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7e9baa4532aa0101efdc239a1e63f2f44d0099b84e442885735042ea198cbf4
|
3 |
+
size 63003985
|
checkpoint-3500/unet_ema/config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.16.1",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": 8,
|
8 |
+
"block_out_channels": [
|
9 |
+
128,
|
10 |
+
128,
|
11 |
+
128,
|
12 |
+
128
|
13 |
+
],
|
14 |
+
"center_input_sample": false,
|
15 |
+
"class_embed_type": null,
|
16 |
+
"class_embeddings_concat": false,
|
17 |
+
"conv_in_kernel": 3,
|
18 |
+
"conv_out_kernel": 3,
|
19 |
+
"cross_attention_dim": 256,
|
20 |
+
"cross_attention_norm": null,
|
21 |
+
"decay": 0.9999,
|
22 |
+
"down_block_types": [
|
23 |
+
"DownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"DownBlock2D"
|
27 |
+
],
|
28 |
+
"downsample_padding": 1,
|
29 |
+
"dual_cross_attention": false,
|
30 |
+
"encoder_hid_dim": null,
|
31 |
+
"flip_sin_to_cos": true,
|
32 |
+
"freq_shift": 0,
|
33 |
+
"in_channels": 3,
|
34 |
+
"inv_gamma": 1.0,
|
35 |
+
"layers_per_block": 2,
|
36 |
+
"mid_block_only_cross_attention": null,
|
37 |
+
"mid_block_scale_factor": 1,
|
38 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
39 |
+
"min_decay": 0.0,
|
40 |
+
"norm_eps": 1e-05,
|
41 |
+
"norm_num_groups": 32,
|
42 |
+
"num_class_embeds": null,
|
43 |
+
"only_cross_attention": false,
|
44 |
+
"optimization_step": 3500,
|
45 |
+
"out_channels": 3,
|
46 |
+
"power": 0.75,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 256,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"up_block_types": [
|
58 |
+
"UpBlock2D",
|
59 |
+
"CrossAttnUpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"UpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"update_after_step": 0,
|
65 |
+
"use_ema_warmup": true,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
checkpoint-3500/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33a5e30513ad17bc19ab95e93c94b4f6cd37bb4d9793c24cb958d2719041a334
|
3 |
+
size 62996305
|
checkpoint-4000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc88c49ac0341b1f028adfe4a415d13b45e4d211b79c0906e55666dd9cb64ccb
|
3 |
+
size 126008021
|