End of training
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- 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 +73 -0
- checkpoint-1000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-1000/unet_ema/config.json +80 -0
- checkpoint-1000/unet_ema/diffusion_pytorch_model.safetensors +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 +73 -0
- checkpoint-1500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-1500/unet_ema/config.json +80 -0
- checkpoint-1500/unet_ema/diffusion_pytorch_model.safetensors +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 +73 -0
- checkpoint-2000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-2000/unet_ema/config.json +80 -0
- checkpoint-2000/unet_ema/diffusion_pytorch_model.safetensors +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 +73 -0
- checkpoint-2500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-2500/unet_ema/config.json +80 -0
- checkpoint-2500/unet_ema/diffusion_pytorch_model.safetensors +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 +73 -0
- checkpoint-3000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-3000/unet_ema/config.json +80 -0
- checkpoint-3000/unet_ema/diffusion_pytorch_model.safetensors +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 +73 -0
- checkpoint-3500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-3500/unet_ema/config.json +80 -0
- checkpoint-3500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-4000/optimizer.bin +3 -0
- checkpoint-4000/random_states_0.pkl +3 -0
checkpoint-1000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64953c50de49e6d32448011a614d60f94d5fdc72457ef7aa4231055a0f720364
|
3 |
+
size 6927867155
|
checkpoint-1000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec4168cdd8e787bdcdc791c4943b74d6afe8a53e00e9738e88ae1b8cd26db59f
|
3 |
+
size 15627
|
checkpoint-1000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68cff80b680ddf6e7abbef98b5f336b97f9b5963e2209307f639383870e8cc71
|
3 |
+
size 557
|
checkpoint-1000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfe94afd21b04fe331bf93a36e6de4869425c4da4a32303493f7f8b96dd6ca61
|
3 |
+
size 563
|
checkpoint-1000/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
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 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"DownBlock2D"
|
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 |
+
"flip_sin_to_cos": true,
|
41 |
+
"freq_shift": 0,
|
42 |
+
"in_channels": 4,
|
43 |
+
"layers_per_block": 2,
|
44 |
+
"mid_block_only_cross_attention": null,
|
45 |
+
"mid_block_scale_factor": 1,
|
46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
47 |
+
"norm_eps": 1e-05,
|
48 |
+
"norm_num_groups": 32,
|
49 |
+
"num_attention_heads": null,
|
50 |
+
"num_class_embeds": null,
|
51 |
+
"only_cross_attention": false,
|
52 |
+
"out_channels": 4,
|
53 |
+
"projection_class_embeddings_input_dim": null,
|
54 |
+
"resnet_out_scale_factor": 1.0,
|
55 |
+
"resnet_skip_time_act": false,
|
56 |
+
"resnet_time_scale_shift": "default",
|
57 |
+
"reverse_transformer_layers_per_block": null,
|
58 |
+
"sample_size": 64,
|
59 |
+
"time_cond_proj_dim": null,
|
60 |
+
"time_embedding_act_fn": null,
|
61 |
+
"time_embedding_dim": null,
|
62 |
+
"time_embedding_type": "positional",
|
63 |
+
"timestep_post_act": null,
|
64 |
+
"transformer_layers_per_block": 1,
|
65 |
+
"up_block_types": [
|
66 |
+
"UpBlock2D",
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"CrossAttnUpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": false,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-1000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a47d1f4093448ec25977d0826739bf44ba02f0a902cbbe8915d6246caa23a2b5
|
3 |
+
size 3463726504
|
checkpoint-1000/unet_ema/config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
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 |
+
"decay": 0.9999,
|
30 |
+
"down_block_types": [
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"CrossAttnDownBlock2D",
|
34 |
+
"DownBlock2D"
|
35 |
+
],
|
36 |
+
"downsample_padding": 1,
|
37 |
+
"dropout": 0.0,
|
38 |
+
"dual_cross_attention": false,
|
39 |
+
"encoder_hid_dim": null,
|
40 |
+
"encoder_hid_dim_type": null,
|
41 |
+
"flip_sin_to_cos": true,
|
42 |
+
"freq_shift": 0,
|
43 |
+
"in_channels": 4,
|
44 |
+
"inv_gamma": 1.0,
|
45 |
+
"layers_per_block": 2,
|
46 |
+
"mid_block_only_cross_attention": null,
|
47 |
+
"mid_block_scale_factor": 1,
|
48 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
49 |
+
"min_decay": 0.0,
|
50 |
+
"norm_eps": 1e-05,
|
51 |
+
"norm_num_groups": 32,
|
52 |
+
"num_attention_heads": null,
|
53 |
+
"num_class_embeds": null,
|
54 |
+
"only_cross_attention": false,
|
55 |
+
"optimization_step": 1000,
|
56 |
+
"out_channels": 4,
|
57 |
+
"power": 0.6666666666666666,
|
58 |
+
"projection_class_embeddings_input_dim": null,
|
59 |
+
"resnet_out_scale_factor": 1.0,
|
60 |
+
"resnet_skip_time_act": false,
|
61 |
+
"resnet_time_scale_shift": "default",
|
62 |
+
"reverse_transformer_layers_per_block": null,
|
63 |
+
"sample_size": 64,
|
64 |
+
"time_cond_proj_dim": null,
|
65 |
+
"time_embedding_act_fn": null,
|
66 |
+
"time_embedding_dim": null,
|
67 |
+
"time_embedding_type": "positional",
|
68 |
+
"timestep_post_act": null,
|
69 |
+
"transformer_layers_per_block": 1,
|
70 |
+
"up_block_types": [
|
71 |
+
"UpBlock2D",
|
72 |
+
"CrossAttnUpBlock2D",
|
73 |
+
"CrossAttnUpBlock2D",
|
74 |
+
"CrossAttnUpBlock2D"
|
75 |
+
],
|
76 |
+
"upcast_attention": false,
|
77 |
+
"update_after_step": 0,
|
78 |
+
"use_ema_warmup": false,
|
79 |
+
"use_linear_projection": true
|
80 |
+
}
|
checkpoint-1000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:947d8a7b46e8695d5065e18413acd8b636eddb7eb7efbe840f37349ed86a6d27
|
3 |
+
size 3463726504
|
checkpoint-1500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb793e3c3298f6aa858052b198a939544d666b6f7ce39080feb95557405320e2
|
3 |
+
size 6927867155
|
checkpoint-1500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67e41f97eda7bd8f1e8aa1167dd685220fe4a449cafe40e005ac7f08cd96a20c
|
3 |
+
size 15627
|
checkpoint-1500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:203a72d6c29f42a0e2964fdddc8d7a98df1eccee78fea9de0fa416613390f5c6
|
3 |
+
size 557
|
checkpoint-1500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d6ec0338061ab706b1805a9e2966ca126b26619cd90bb73133127681b9de370
|
3 |
+
size 563
|
checkpoint-1500/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
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 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"DownBlock2D"
|
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 |
+
"flip_sin_to_cos": true,
|
41 |
+
"freq_shift": 0,
|
42 |
+
"in_channels": 4,
|
43 |
+
"layers_per_block": 2,
|
44 |
+
"mid_block_only_cross_attention": null,
|
45 |
+
"mid_block_scale_factor": 1,
|
46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
47 |
+
"norm_eps": 1e-05,
|
48 |
+
"norm_num_groups": 32,
|
49 |
+
"num_attention_heads": null,
|
50 |
+
"num_class_embeds": null,
|
51 |
+
"only_cross_attention": false,
|
52 |
+
"out_channels": 4,
|
53 |
+
"projection_class_embeddings_input_dim": null,
|
54 |
+
"resnet_out_scale_factor": 1.0,
|
55 |
+
"resnet_skip_time_act": false,
|
56 |
+
"resnet_time_scale_shift": "default",
|
57 |
+
"reverse_transformer_layers_per_block": null,
|
58 |
+
"sample_size": 64,
|
59 |
+
"time_cond_proj_dim": null,
|
60 |
+
"time_embedding_act_fn": null,
|
61 |
+
"time_embedding_dim": null,
|
62 |
+
"time_embedding_type": "positional",
|
63 |
+
"timestep_post_act": null,
|
64 |
+
"transformer_layers_per_block": 1,
|
65 |
+
"up_block_types": [
|
66 |
+
"UpBlock2D",
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"CrossAttnUpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": false,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-1500/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ee6bbbbb40a7f5e3a72ddc181a3d89966a031002a92d4f61ce4b08f19a2dd3c
|
3 |
+
size 3463726504
|
checkpoint-1500/unet_ema/config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
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 |
+
"decay": 0.9999,
|
30 |
+
"down_block_types": [
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"CrossAttnDownBlock2D",
|
34 |
+
"DownBlock2D"
|
35 |
+
],
|
36 |
+
"downsample_padding": 1,
|
37 |
+
"dropout": 0.0,
|
38 |
+
"dual_cross_attention": false,
|
39 |
+
"encoder_hid_dim": null,
|
40 |
+
"encoder_hid_dim_type": null,
|
41 |
+
"flip_sin_to_cos": true,
|
42 |
+
"freq_shift": 0,
|
43 |
+
"in_channels": 4,
|
44 |
+
"inv_gamma": 1.0,
|
45 |
+
"layers_per_block": 2,
|
46 |
+
"mid_block_only_cross_attention": null,
|
47 |
+
"mid_block_scale_factor": 1,
|
48 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
49 |
+
"min_decay": 0.0,
|
50 |
+
"norm_eps": 1e-05,
|
51 |
+
"norm_num_groups": 32,
|
52 |
+
"num_attention_heads": null,
|
53 |
+
"num_class_embeds": null,
|
54 |
+
"only_cross_attention": false,
|
55 |
+
"optimization_step": 1500,
|
56 |
+
"out_channels": 4,
|
57 |
+
"power": 0.6666666666666666,
|
58 |
+
"projection_class_embeddings_input_dim": null,
|
59 |
+
"resnet_out_scale_factor": 1.0,
|
60 |
+
"resnet_skip_time_act": false,
|
61 |
+
"resnet_time_scale_shift": "default",
|
62 |
+
"reverse_transformer_layers_per_block": null,
|
63 |
+
"sample_size": 64,
|
64 |
+
"time_cond_proj_dim": null,
|
65 |
+
"time_embedding_act_fn": null,
|
66 |
+
"time_embedding_dim": null,
|
67 |
+
"time_embedding_type": "positional",
|
68 |
+
"timestep_post_act": null,
|
69 |
+
"transformer_layers_per_block": 1,
|
70 |
+
"up_block_types": [
|
71 |
+
"UpBlock2D",
|
72 |
+
"CrossAttnUpBlock2D",
|
73 |
+
"CrossAttnUpBlock2D",
|
74 |
+
"CrossAttnUpBlock2D"
|
75 |
+
],
|
76 |
+
"upcast_attention": false,
|
77 |
+
"update_after_step": 0,
|
78 |
+
"use_ema_warmup": false,
|
79 |
+
"use_linear_projection": true
|
80 |
+
}
|
checkpoint-1500/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7728b530dfcc9ea42c4380d4fa43f37bb20a7e7ea98ac3888a7b4cc34d78b840
|
3 |
+
size 3463726504
|
checkpoint-2000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0780dcd035462b9ebe96283f7bb41e8468d28e2e8b96e2335d8de12fc087e134
|
3 |
+
size 6927867155
|
checkpoint-2000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:327a988116794d6728a6e4f6228be2d3935fca3872cec27fa65ef4544c3ee920
|
3 |
+
size 15627
|
checkpoint-2000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd2de9749828adacdf103bf6e9592702bb7067a2c1df27dd62ab38c1eb8c070f
|
3 |
+
size 557
|
checkpoint-2000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7edd8082ac389d0c946c2ac507fc3e4d21eaad8a44fcb3f7b57ebbd1b62363dc
|
3 |
+
size 563
|
checkpoint-2000/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
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 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"DownBlock2D"
|
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 |
+
"flip_sin_to_cos": true,
|
41 |
+
"freq_shift": 0,
|
42 |
+
"in_channels": 4,
|
43 |
+
"layers_per_block": 2,
|
44 |
+
"mid_block_only_cross_attention": null,
|
45 |
+
"mid_block_scale_factor": 1,
|
46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
47 |
+
"norm_eps": 1e-05,
|
48 |
+
"norm_num_groups": 32,
|
49 |
+
"num_attention_heads": null,
|
50 |
+
"num_class_embeds": null,
|
51 |
+
"only_cross_attention": false,
|
52 |
+
"out_channels": 4,
|
53 |
+
"projection_class_embeddings_input_dim": null,
|
54 |
+
"resnet_out_scale_factor": 1.0,
|
55 |
+
"resnet_skip_time_act": false,
|
56 |
+
"resnet_time_scale_shift": "default",
|
57 |
+
"reverse_transformer_layers_per_block": null,
|
58 |
+
"sample_size": 64,
|
59 |
+
"time_cond_proj_dim": null,
|
60 |
+
"time_embedding_act_fn": null,
|
61 |
+
"time_embedding_dim": null,
|
62 |
+
"time_embedding_type": "positional",
|
63 |
+
"timestep_post_act": null,
|
64 |
+
"transformer_layers_per_block": 1,
|
65 |
+
"up_block_types": [
|
66 |
+
"UpBlock2D",
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"CrossAttnUpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": false,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-2000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b27f54f53d6f23db1f1eddf916916be35ac0b18f1970e9cebf0e54335d466e9
|
3 |
+
size 3463726504
|
checkpoint-2000/unet_ema/config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
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 |
+
"decay": 0.9999,
|
30 |
+
"down_block_types": [
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"CrossAttnDownBlock2D",
|
34 |
+
"DownBlock2D"
|
35 |
+
],
|
36 |
+
"downsample_padding": 1,
|
37 |
+
"dropout": 0.0,
|
38 |
+
"dual_cross_attention": false,
|
39 |
+
"encoder_hid_dim": null,
|
40 |
+
"encoder_hid_dim_type": null,
|
41 |
+
"flip_sin_to_cos": true,
|
42 |
+
"freq_shift": 0,
|
43 |
+
"in_channels": 4,
|
44 |
+
"inv_gamma": 1.0,
|
45 |
+
"layers_per_block": 2,
|
46 |
+
"mid_block_only_cross_attention": null,
|
47 |
+
"mid_block_scale_factor": 1,
|
48 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
49 |
+
"min_decay": 0.0,
|
50 |
+
"norm_eps": 1e-05,
|
51 |
+
"norm_num_groups": 32,
|
52 |
+
"num_attention_heads": null,
|
53 |
+
"num_class_embeds": null,
|
54 |
+
"only_cross_attention": false,
|
55 |
+
"optimization_step": 2000,
|
56 |
+
"out_channels": 4,
|
57 |
+
"power": 0.6666666666666666,
|
58 |
+
"projection_class_embeddings_input_dim": null,
|
59 |
+
"resnet_out_scale_factor": 1.0,
|
60 |
+
"resnet_skip_time_act": false,
|
61 |
+
"resnet_time_scale_shift": "default",
|
62 |
+
"reverse_transformer_layers_per_block": null,
|
63 |
+
"sample_size": 64,
|
64 |
+
"time_cond_proj_dim": null,
|
65 |
+
"time_embedding_act_fn": null,
|
66 |
+
"time_embedding_dim": null,
|
67 |
+
"time_embedding_type": "positional",
|
68 |
+
"timestep_post_act": null,
|
69 |
+
"transformer_layers_per_block": 1,
|
70 |
+
"up_block_types": [
|
71 |
+
"UpBlock2D",
|
72 |
+
"CrossAttnUpBlock2D",
|
73 |
+
"CrossAttnUpBlock2D",
|
74 |
+
"CrossAttnUpBlock2D"
|
75 |
+
],
|
76 |
+
"upcast_attention": false,
|
77 |
+
"update_after_step": 0,
|
78 |
+
"use_ema_warmup": false,
|
79 |
+
"use_linear_projection": true
|
80 |
+
}
|
checkpoint-2000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68ed674dd5d8b3b348e06391d2290f85d2ac97f79215c6c9a38137b27655951f
|
3 |
+
size 3463726504
|
checkpoint-2500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad91bae2177aea70b34317832230238c98b4dad77e88fe11562ff2b20c00c5e1
|
3 |
+
size 6927867155
|
checkpoint-2500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e764ed56362fe9dfc114e63cb7b64e5732d31039c9aedc0980d82190f460408
|
3 |
+
size 15627
|
checkpoint-2500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fbcebc8f5487b0c117b5dd47f2ea304af3eebf408d297118d9307e1223927e1
|
3 |
+
size 557
|
checkpoint-2500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00b6b035e89b3f614d8a7babea59ef588908ea69ffc4eb871a24c002d6356cdc
|
3 |
+
size 563
|
checkpoint-2500/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
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 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"DownBlock2D"
|
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 |
+
"flip_sin_to_cos": true,
|
41 |
+
"freq_shift": 0,
|
42 |
+
"in_channels": 4,
|
43 |
+
"layers_per_block": 2,
|
44 |
+
"mid_block_only_cross_attention": null,
|
45 |
+
"mid_block_scale_factor": 1,
|
46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
47 |
+
"norm_eps": 1e-05,
|
48 |
+
"norm_num_groups": 32,
|
49 |
+
"num_attention_heads": null,
|
50 |
+
"num_class_embeds": null,
|
51 |
+
"only_cross_attention": false,
|
52 |
+
"out_channels": 4,
|
53 |
+
"projection_class_embeddings_input_dim": null,
|
54 |
+
"resnet_out_scale_factor": 1.0,
|
55 |
+
"resnet_skip_time_act": false,
|
56 |
+
"resnet_time_scale_shift": "default",
|
57 |
+
"reverse_transformer_layers_per_block": null,
|
58 |
+
"sample_size": 64,
|
59 |
+
"time_cond_proj_dim": null,
|
60 |
+
"time_embedding_act_fn": null,
|
61 |
+
"time_embedding_dim": null,
|
62 |
+
"time_embedding_type": "positional",
|
63 |
+
"timestep_post_act": null,
|
64 |
+
"transformer_layers_per_block": 1,
|
65 |
+
"up_block_types": [
|
66 |
+
"UpBlock2D",
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"CrossAttnUpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": false,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-2500/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9b865bbd57a5813e2e56697cbec0cd913fc1af9ceb30bd744923fc0179c4d80
|
3 |
+
size 3463726504
|
checkpoint-2500/unet_ema/config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
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 |
+
"decay": 0.9999,
|
30 |
+
"down_block_types": [
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"CrossAttnDownBlock2D",
|
34 |
+
"DownBlock2D"
|
35 |
+
],
|
36 |
+
"downsample_padding": 1,
|
37 |
+
"dropout": 0.0,
|
38 |
+
"dual_cross_attention": false,
|
39 |
+
"encoder_hid_dim": null,
|
40 |
+
"encoder_hid_dim_type": null,
|
41 |
+
"flip_sin_to_cos": true,
|
42 |
+
"freq_shift": 0,
|
43 |
+
"in_channels": 4,
|
44 |
+
"inv_gamma": 1.0,
|
45 |
+
"layers_per_block": 2,
|
46 |
+
"mid_block_only_cross_attention": null,
|
47 |
+
"mid_block_scale_factor": 1,
|
48 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
49 |
+
"min_decay": 0.0,
|
50 |
+
"norm_eps": 1e-05,
|
51 |
+
"norm_num_groups": 32,
|
52 |
+
"num_attention_heads": null,
|
53 |
+
"num_class_embeds": null,
|
54 |
+
"only_cross_attention": false,
|
55 |
+
"optimization_step": 2500,
|
56 |
+
"out_channels": 4,
|
57 |
+
"power": 0.6666666666666666,
|
58 |
+
"projection_class_embeddings_input_dim": null,
|
59 |
+
"resnet_out_scale_factor": 1.0,
|
60 |
+
"resnet_skip_time_act": false,
|
61 |
+
"resnet_time_scale_shift": "default",
|
62 |
+
"reverse_transformer_layers_per_block": null,
|
63 |
+
"sample_size": 64,
|
64 |
+
"time_cond_proj_dim": null,
|
65 |
+
"time_embedding_act_fn": null,
|
66 |
+
"time_embedding_dim": null,
|
67 |
+
"time_embedding_type": "positional",
|
68 |
+
"timestep_post_act": null,
|
69 |
+
"transformer_layers_per_block": 1,
|
70 |
+
"up_block_types": [
|
71 |
+
"UpBlock2D",
|
72 |
+
"CrossAttnUpBlock2D",
|
73 |
+
"CrossAttnUpBlock2D",
|
74 |
+
"CrossAttnUpBlock2D"
|
75 |
+
],
|
76 |
+
"upcast_attention": false,
|
77 |
+
"update_after_step": 0,
|
78 |
+
"use_ema_warmup": false,
|
79 |
+
"use_linear_projection": true
|
80 |
+
}
|
checkpoint-2500/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c06eecce9304fd63cc0f6b2ba3e84d42c299ff503aa8db97fde07161d04aa74
|
3 |
+
size 3463726504
|
checkpoint-3000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c83d3013b41fc22bcda1707770c9f18b24371a36ecb5eae13fec78fe1cfabb6
|
3 |
+
size 6927867155
|
checkpoint-3000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec16fad4d2d0985e759f80a9146ca2abc9d4565ed1b4e4fdd0e94848aee9a81d
|
3 |
+
size 15627
|
checkpoint-3000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb1f9398b77268202e8e1465734a63d123b1ef11c27f20f2473677e9883a6869
|
3 |
+
size 557
|
checkpoint-3000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a0df2dffc0559ef6134e0571ccfecb406ec3a612efe566ae6f1c62bcf1ab353
|
3 |
+
size 563
|
checkpoint-3000/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
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 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"DownBlock2D"
|
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 |
+
"flip_sin_to_cos": true,
|
41 |
+
"freq_shift": 0,
|
42 |
+
"in_channels": 4,
|
43 |
+
"layers_per_block": 2,
|
44 |
+
"mid_block_only_cross_attention": null,
|
45 |
+
"mid_block_scale_factor": 1,
|
46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
47 |
+
"norm_eps": 1e-05,
|
48 |
+
"norm_num_groups": 32,
|
49 |
+
"num_attention_heads": null,
|
50 |
+
"num_class_embeds": null,
|
51 |
+
"only_cross_attention": false,
|
52 |
+
"out_channels": 4,
|
53 |
+
"projection_class_embeddings_input_dim": null,
|
54 |
+
"resnet_out_scale_factor": 1.0,
|
55 |
+
"resnet_skip_time_act": false,
|
56 |
+
"resnet_time_scale_shift": "default",
|
57 |
+
"reverse_transformer_layers_per_block": null,
|
58 |
+
"sample_size": 64,
|
59 |
+
"time_cond_proj_dim": null,
|
60 |
+
"time_embedding_act_fn": null,
|
61 |
+
"time_embedding_dim": null,
|
62 |
+
"time_embedding_type": "positional",
|
63 |
+
"timestep_post_act": null,
|
64 |
+
"transformer_layers_per_block": 1,
|
65 |
+
"up_block_types": [
|
66 |
+
"UpBlock2D",
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"CrossAttnUpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": false,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-3000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a72b393939df5c5653540484fa526104dcd16b364be23287d296b5ba6a5fe217
|
3 |
+
size 3463726504
|
checkpoint-3000/unet_ema/config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
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 |
+
"decay": 0.9999,
|
30 |
+
"down_block_types": [
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"CrossAttnDownBlock2D",
|
34 |
+
"DownBlock2D"
|
35 |
+
],
|
36 |
+
"downsample_padding": 1,
|
37 |
+
"dropout": 0.0,
|
38 |
+
"dual_cross_attention": false,
|
39 |
+
"encoder_hid_dim": null,
|
40 |
+
"encoder_hid_dim_type": null,
|
41 |
+
"flip_sin_to_cos": true,
|
42 |
+
"freq_shift": 0,
|
43 |
+
"in_channels": 4,
|
44 |
+
"inv_gamma": 1.0,
|
45 |
+
"layers_per_block": 2,
|
46 |
+
"mid_block_only_cross_attention": null,
|
47 |
+
"mid_block_scale_factor": 1,
|
48 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
49 |
+
"min_decay": 0.0,
|
50 |
+
"norm_eps": 1e-05,
|
51 |
+
"norm_num_groups": 32,
|
52 |
+
"num_attention_heads": null,
|
53 |
+
"num_class_embeds": null,
|
54 |
+
"only_cross_attention": false,
|
55 |
+
"optimization_step": 3000,
|
56 |
+
"out_channels": 4,
|
57 |
+
"power": 0.6666666666666666,
|
58 |
+
"projection_class_embeddings_input_dim": null,
|
59 |
+
"resnet_out_scale_factor": 1.0,
|
60 |
+
"resnet_skip_time_act": false,
|
61 |
+
"resnet_time_scale_shift": "default",
|
62 |
+
"reverse_transformer_layers_per_block": null,
|
63 |
+
"sample_size": 64,
|
64 |
+
"time_cond_proj_dim": null,
|
65 |
+
"time_embedding_act_fn": null,
|
66 |
+
"time_embedding_dim": null,
|
67 |
+
"time_embedding_type": "positional",
|
68 |
+
"timestep_post_act": null,
|
69 |
+
"transformer_layers_per_block": 1,
|
70 |
+
"up_block_types": [
|
71 |
+
"UpBlock2D",
|
72 |
+
"CrossAttnUpBlock2D",
|
73 |
+
"CrossAttnUpBlock2D",
|
74 |
+
"CrossAttnUpBlock2D"
|
75 |
+
],
|
76 |
+
"upcast_attention": false,
|
77 |
+
"update_after_step": 0,
|
78 |
+
"use_ema_warmup": false,
|
79 |
+
"use_linear_projection": true
|
80 |
+
}
|
checkpoint-3000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04fc1e659683bdc6608f4437d59343d3d864ca7f7880052729a561c4fb0597ac
|
3 |
+
size 3463726504
|
checkpoint-3500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b585f31ec035f4a85ec069a850414a5013a634e5652ca75fb44239c4b081f676
|
3 |
+
size 6927867155
|
checkpoint-3500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49fa097c2ec602227a1bc7c8b21a655555d5aa1c74e4c1c64529528fd5c461eb
|
3 |
+
size 15627
|
checkpoint-3500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4cfe72973031c5a482f6e9ed0cb664a6aa7f63116e294e2b1f72d360d9b033c
|
3 |
+
size 557
|
checkpoint-3500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0e6cbbd05427cb09a990f303190d8f0051084080c856964101f9aea5e481068
|
3 |
+
size 563
|
checkpoint-3500/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
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 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"DownBlock2D"
|
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 |
+
"flip_sin_to_cos": true,
|
41 |
+
"freq_shift": 0,
|
42 |
+
"in_channels": 4,
|
43 |
+
"layers_per_block": 2,
|
44 |
+
"mid_block_only_cross_attention": null,
|
45 |
+
"mid_block_scale_factor": 1,
|
46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
47 |
+
"norm_eps": 1e-05,
|
48 |
+
"norm_num_groups": 32,
|
49 |
+
"num_attention_heads": null,
|
50 |
+
"num_class_embeds": null,
|
51 |
+
"only_cross_attention": false,
|
52 |
+
"out_channels": 4,
|
53 |
+
"projection_class_embeddings_input_dim": null,
|
54 |
+
"resnet_out_scale_factor": 1.0,
|
55 |
+
"resnet_skip_time_act": false,
|
56 |
+
"resnet_time_scale_shift": "default",
|
57 |
+
"reverse_transformer_layers_per_block": null,
|
58 |
+
"sample_size": 64,
|
59 |
+
"time_cond_proj_dim": null,
|
60 |
+
"time_embedding_act_fn": null,
|
61 |
+
"time_embedding_dim": null,
|
62 |
+
"time_embedding_type": "positional",
|
63 |
+
"timestep_post_act": null,
|
64 |
+
"transformer_layers_per_block": 1,
|
65 |
+
"up_block_types": [
|
66 |
+
"UpBlock2D",
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"CrossAttnUpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": false,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-3500/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd0b1d1177bd3c3e363b591962d510581236e01906264928170ced24ab8ea404
|
3 |
+
size 3463726504
|
checkpoint-3500/unet_ema/config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
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 |
+
"decay": 0.9999,
|
30 |
+
"down_block_types": [
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"CrossAttnDownBlock2D",
|
34 |
+
"DownBlock2D"
|
35 |
+
],
|
36 |
+
"downsample_padding": 1,
|
37 |
+
"dropout": 0.0,
|
38 |
+
"dual_cross_attention": false,
|
39 |
+
"encoder_hid_dim": null,
|
40 |
+
"encoder_hid_dim_type": null,
|
41 |
+
"flip_sin_to_cos": true,
|
42 |
+
"freq_shift": 0,
|
43 |
+
"in_channels": 4,
|
44 |
+
"inv_gamma": 1.0,
|
45 |
+
"layers_per_block": 2,
|
46 |
+
"mid_block_only_cross_attention": null,
|
47 |
+
"mid_block_scale_factor": 1,
|
48 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
49 |
+
"min_decay": 0.0,
|
50 |
+
"norm_eps": 1e-05,
|
51 |
+
"norm_num_groups": 32,
|
52 |
+
"num_attention_heads": null,
|
53 |
+
"num_class_embeds": null,
|
54 |
+
"only_cross_attention": false,
|
55 |
+
"optimization_step": 3500,
|
56 |
+
"out_channels": 4,
|
57 |
+
"power": 0.6666666666666666,
|
58 |
+
"projection_class_embeddings_input_dim": null,
|
59 |
+
"resnet_out_scale_factor": 1.0,
|
60 |
+
"resnet_skip_time_act": false,
|
61 |
+
"resnet_time_scale_shift": "default",
|
62 |
+
"reverse_transformer_layers_per_block": null,
|
63 |
+
"sample_size": 64,
|
64 |
+
"time_cond_proj_dim": null,
|
65 |
+
"time_embedding_act_fn": null,
|
66 |
+
"time_embedding_dim": null,
|
67 |
+
"time_embedding_type": "positional",
|
68 |
+
"timestep_post_act": null,
|
69 |
+
"transformer_layers_per_block": 1,
|
70 |
+
"up_block_types": [
|
71 |
+
"UpBlock2D",
|
72 |
+
"CrossAttnUpBlock2D",
|
73 |
+
"CrossAttnUpBlock2D",
|
74 |
+
"CrossAttnUpBlock2D"
|
75 |
+
],
|
76 |
+
"upcast_attention": false,
|
77 |
+
"update_after_step": 0,
|
78 |
+
"use_ema_warmup": false,
|
79 |
+
"use_linear_projection": true
|
80 |
+
}
|
checkpoint-3500/unet_ema/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c2036278e2b1aa4e9097f10c2367dc05937c16cc58b2d4d3218b178a8b600c3
|
3 |
+
size 3463726504
|
checkpoint-4000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1bc3bf20981b711baa1fa090adc8c29079bc914309e7a88458c23bf82947772
|
3 |
+
size 6927867155
|
checkpoint-4000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adeee901e3afaa5e7e89cd129306350877de3ee5f3e692aad52778da5646ce74
|
3 |
+
size 15627
|