Epoch 4
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-14000/optimizer.bin +3 -0
- checkpoint-14000/random_states_0.pkl +3 -0
- checkpoint-14000/scaler.pt +3 -0
- checkpoint-14000/scheduler.bin +3 -0
- checkpoint-14000/unet/config.json +60 -0
- checkpoint-14000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-14000/unet_ema/config.json +67 -0
- checkpoint-14000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-14500/optimizer.bin +3 -0
- checkpoint-14500/random_states_0.pkl +3 -0
- checkpoint-14500/scaler.pt +3 -0
- checkpoint-14500/scheduler.bin +3 -0
- checkpoint-14500/unet/config.json +60 -0
- checkpoint-14500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-14500/unet_ema/config.json +67 -0
- checkpoint-14500/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-15000/optimizer.bin +3 -0
- checkpoint-15000/random_states_0.pkl +3 -0
- checkpoint-15000/scaler.pt +3 -0
- checkpoint-15000/scheduler.bin +3 -0
- checkpoint-15000/unet/config.json +60 -0
- checkpoint-15000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-15000/unet_ema/config.json +67 -0
- checkpoint-15000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-15500/optimizer.bin +3 -0
- checkpoint-15500/random_states_0.pkl +3 -0
- checkpoint-15500/scaler.pt +3 -0
- checkpoint-15500/scheduler.bin +3 -0
- checkpoint-15500/unet/config.json +60 -0
- checkpoint-15500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-15500/unet_ema/config.json +67 -0
- checkpoint-15500/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-16000/optimizer.bin +3 -0
- checkpoint-16000/random_states_0.pkl +3 -0
- checkpoint-16000/scaler.pt +3 -0
- checkpoint-16000/scheduler.bin +3 -0
- checkpoint-16000/unet/config.json +60 -0
- checkpoint-16000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-16000/unet_ema/config.json +67 -0
- checkpoint-16000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-16500/optimizer.bin +3 -0
- checkpoint-16500/random_states_0.pkl +3 -0
- checkpoint-16500/scaler.pt +3 -0
- checkpoint-16500/scheduler.bin +3 -0
- checkpoint-16500/unet/config.json +60 -0
- checkpoint-16500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-16500/unet_ema/config.json +67 -0
- checkpoint-16500/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-17000/optimizer.bin +3 -0
- checkpoint-17000/random_states_0.pkl +3 -0
checkpoint-14000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0517bb14b48b19e4f1412c4a8d64aac91bdac6c25fd2ad38adc03b8ee5023eee
|
3 |
+
size 73251413
|
checkpoint-14000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:472687f5f5a515062c61378f1a9d6cfab6194076c1f58251cd1af62215d61b56
|
3 |
+
size 14663
|
checkpoint-14000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b3be7f0fbd62efda569a6c8c7cbf83d6fd6837abb9ab66cc81285b8584961ad
|
3 |
+
size 557
|
checkpoint-14000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e24b4aad6f64dab61f771e84bbb1801e3f2227353b2322e686479bf7a66bfd4b
|
3 |
+
size 563
|
checkpoint-14000/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 |
+
64,
|
10 |
+
64,
|
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 |
+
"DownBlock2D",
|
24 |
+
"DownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D"
|
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 |
+
"CrossAttnUpBlock2D",
|
54 |
+
"UpBlock2D",
|
55 |
+
"UpBlock2D",
|
56 |
+
"UpBlock2D"
|
57 |
+
],
|
58 |
+
"upcast_attention": false,
|
59 |
+
"use_linear_projection": false
|
60 |
+
}
|
checkpoint-14000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a9fa484752be4574f8b809ba3a33ff8b2d1e733e6011bc13d0ee69a88d1071d
|
3 |
+
size 36621969
|
checkpoint-14000/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 |
+
64,
|
10 |
+
64,
|
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 |
+
"DownBlock2D",
|
25 |
+
"DownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D"
|
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": 14000,
|
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 |
+
"CrossAttnUpBlock2D",
|
59 |
+
"UpBlock2D",
|
60 |
+
"UpBlock2D",
|
61 |
+
"UpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"update_after_step": 0,
|
65 |
+
"use_ema_warmup": true,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
checkpoint-14000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2286497b9a798742b427af91942d4567d146a50a677160397a1b8722f206e4d9
|
3 |
+
size 36616081
|
checkpoint-14500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c031094f5d928638b115eb122f3d7ac334e05199a1d060a0ab9e76763548ebf2
|
3 |
+
size 73251413
|
checkpoint-14500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e68d9dce6e7b98604684485f641e0f29cde33e230cf1d9b0368c103bf06f2e4
|
3 |
+
size 14663
|
checkpoint-14500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5e9e0307b975b40dfaa6bc63ca69f23f79f951ed57dcc9b12a6fef8b46e7601
|
3 |
+
size 557
|
checkpoint-14500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af9e8cd4f94fd0956c7562ceda0191571817d6ee575a7060d8f56b74991f5539
|
3 |
+
size 563
|
checkpoint-14500/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 |
+
64,
|
10 |
+
64,
|
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 |
+
"DownBlock2D",
|
24 |
+
"DownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D"
|
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 |
+
"CrossAttnUpBlock2D",
|
54 |
+
"UpBlock2D",
|
55 |
+
"UpBlock2D",
|
56 |
+
"UpBlock2D"
|
57 |
+
],
|
58 |
+
"upcast_attention": false,
|
59 |
+
"use_linear_projection": false
|
60 |
+
}
|
checkpoint-14500/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a65f89a25e70ffc562755a65018f98facf1eb36e3a786d800c808b11c17eb9fe
|
3 |
+
size 36621969
|
checkpoint-14500/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 |
+
64,
|
10 |
+
64,
|
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 |
+
"DownBlock2D",
|
25 |
+
"DownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D"
|
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": 14500,
|
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 |
+
"CrossAttnUpBlock2D",
|
59 |
+
"UpBlock2D",
|
60 |
+
"UpBlock2D",
|
61 |
+
"UpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"update_after_step": 0,
|
65 |
+
"use_ema_warmup": true,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
checkpoint-14500/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a80ded58e5140b09d67d715c5f26080fb36cdfa7b6c48284a4d01652e8baf4b
|
3 |
+
size 36616081
|
checkpoint-15000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eef3fdbb276cc72f131011e7937f11edc6824372a51f7396aca3b96f0e10e872
|
3 |
+
size 73251413
|
checkpoint-15000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99a120ddfd8f41c2beff8ca61f8737cd4fe6bd45a9cb384459f4709ffa1ebbac
|
3 |
+
size 14663
|
checkpoint-15000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8940a5ee888900c912bdc7125aaa5b1f996847a7901aa3b40c3f550164bd01d1
|
3 |
+
size 557
|
checkpoint-15000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f35c0b151a7a494c0d09798e3931d60a797963171701839b415749342e615be
|
3 |
+
size 563
|
checkpoint-15000/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 |
+
64,
|
10 |
+
64,
|
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 |
+
"DownBlock2D",
|
24 |
+
"DownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D"
|
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 |
+
"CrossAttnUpBlock2D",
|
54 |
+
"UpBlock2D",
|
55 |
+
"UpBlock2D",
|
56 |
+
"UpBlock2D"
|
57 |
+
],
|
58 |
+
"upcast_attention": false,
|
59 |
+
"use_linear_projection": false
|
60 |
+
}
|
checkpoint-15000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:564657229edcf42df401c13cc78eeea5779aba23de345fdcbf0fa568f1674065
|
3 |
+
size 36621969
|
checkpoint-15000/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 |
+
64,
|
10 |
+
64,
|
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 |
+
"DownBlock2D",
|
25 |
+
"DownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D"
|
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": 15000,
|
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 |
+
"CrossAttnUpBlock2D",
|
59 |
+
"UpBlock2D",
|
60 |
+
"UpBlock2D",
|
61 |
+
"UpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"update_after_step": 0,
|
65 |
+
"use_ema_warmup": true,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
checkpoint-15000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44c885ecd11cbc6eb252a616a25a0727dcd839728b9886c71a3f4b692e4630f4
|
3 |
+
size 36616081
|
checkpoint-15500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:073ef3b4ac141d0ae1f9c18d6dac311932151a94227fddd25040581bbba463f1
|
3 |
+
size 73251413
|
checkpoint-15500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8bd77130c3cb7e9fe8258300fb31a0facae3dae81c5915a99338baba572473c
|
3 |
+
size 14663
|
checkpoint-15500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a85ef3b212aecd1b52e59b877029f1530dc833c15fc07e27f43e889897e07c2
|
3 |
+
size 557
|
checkpoint-15500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31ea019ea6895b9a9b410c6ce5797f28dab6b090a61a1a98ba2f77c6a970005e
|
3 |
+
size 563
|
checkpoint-15500/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 |
+
64,
|
10 |
+
64,
|
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 |
+
"DownBlock2D",
|
24 |
+
"DownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D"
|
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 |
+
"CrossAttnUpBlock2D",
|
54 |
+
"UpBlock2D",
|
55 |
+
"UpBlock2D",
|
56 |
+
"UpBlock2D"
|
57 |
+
],
|
58 |
+
"upcast_attention": false,
|
59 |
+
"use_linear_projection": false
|
60 |
+
}
|
checkpoint-15500/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b83f8c4137be123d2dde8a03da1d97b19346bb906ccb4f126f07203fc887769
|
3 |
+
size 36621969
|
checkpoint-15500/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 |
+
64,
|
10 |
+
64,
|
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 |
+
"DownBlock2D",
|
25 |
+
"DownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D"
|
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": 15500,
|
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 |
+
"CrossAttnUpBlock2D",
|
59 |
+
"UpBlock2D",
|
60 |
+
"UpBlock2D",
|
61 |
+
"UpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"update_after_step": 0,
|
65 |
+
"use_ema_warmup": true,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
checkpoint-15500/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1374481e542334e46fb8d590c48437081045e2b306e429b62a519b7158b45da
|
3 |
+
size 36616081
|
checkpoint-16000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:532f347de31391c73d1f66e3800e752625d0e8764c8695e74f4e26605898191b
|
3 |
+
size 73251413
|
checkpoint-16000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da33f1c6b052efd4c33c0c3ec483b6b3a9557e6b8aaee2539bc5d9db0677a336
|
3 |
+
size 14663
|
checkpoint-16000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e80750edaf752ce95f670438e27cf94261c295db73db5c4dec29b806faa4cbe3
|
3 |
+
size 557
|
checkpoint-16000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6cc3dda7733b36e39c7140c42fa0eb6bf789a9fcfb5dc64a708286d8d0ab9ff
|
3 |
+
size 563
|
checkpoint-16000/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 |
+
64,
|
10 |
+
64,
|
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 |
+
"DownBlock2D",
|
24 |
+
"DownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D"
|
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 |
+
"CrossAttnUpBlock2D",
|
54 |
+
"UpBlock2D",
|
55 |
+
"UpBlock2D",
|
56 |
+
"UpBlock2D"
|
57 |
+
],
|
58 |
+
"upcast_attention": false,
|
59 |
+
"use_linear_projection": false
|
60 |
+
}
|
checkpoint-16000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f2d652b372bae448fb48188acdf90bb381fd3c6d4774f646560b42848d79122
|
3 |
+
size 36621969
|
checkpoint-16000/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 |
+
64,
|
10 |
+
64,
|
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 |
+
"DownBlock2D",
|
25 |
+
"DownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D"
|
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": 16000,
|
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 |
+
"CrossAttnUpBlock2D",
|
59 |
+
"UpBlock2D",
|
60 |
+
"UpBlock2D",
|
61 |
+
"UpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"update_after_step": 0,
|
65 |
+
"use_ema_warmup": true,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
checkpoint-16000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a2b3fdd57f63aa489a6aa722fe654141be7790520734547e8f6fb27f12daadf
|
3 |
+
size 36616081
|
checkpoint-16500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e480ba8fa7a19ec719e4105ae0c7ff483964fe1b797a716c1369537a74749542
|
3 |
+
size 73251413
|
checkpoint-16500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d41aefe0bbf10da4ff04f6c836b77665cde4e3d4054a39e7fc8d1864c616fc3
|
3 |
+
size 14663
|
checkpoint-16500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cb80a41cf77edff81ced0413469d5e0e43be6ea32667facd2ee8a2b8b7f6464
|
3 |
+
size 557
|
checkpoint-16500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10ba4942321e4a1700cc46723f7941ba2e0385c9b74fdfbffbb75ea9340f8325
|
3 |
+
size 563
|
checkpoint-16500/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 |
+
64,
|
10 |
+
64,
|
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 |
+
"DownBlock2D",
|
24 |
+
"DownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D"
|
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 |
+
"CrossAttnUpBlock2D",
|
54 |
+
"UpBlock2D",
|
55 |
+
"UpBlock2D",
|
56 |
+
"UpBlock2D"
|
57 |
+
],
|
58 |
+
"upcast_attention": false,
|
59 |
+
"use_linear_projection": false
|
60 |
+
}
|
checkpoint-16500/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e17539657601d1d12e6454fa7d2a8417162c283360fc19c05e66bd6b9dd882d7
|
3 |
+
size 36621969
|
checkpoint-16500/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 |
+
64,
|
10 |
+
64,
|
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 |
+
"DownBlock2D",
|
25 |
+
"DownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D"
|
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": 16500,
|
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 |
+
"CrossAttnUpBlock2D",
|
59 |
+
"UpBlock2D",
|
60 |
+
"UpBlock2D",
|
61 |
+
"UpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"update_after_step": 0,
|
65 |
+
"use_ema_warmup": true,
|
66 |
+
"use_linear_projection": false
|
67 |
+
}
|
checkpoint-16500/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e972c9dc07c8005edb34c8dde598b7889af0c855c526dae009824fbb0c32b61
|
3 |
+
size 36616081
|
checkpoint-17000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dda86f51949173874b1eb5c075e5bc721eff91f224eca430dbeda4370e082de6
|
3 |
+
size 73251413
|
checkpoint-17000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:838a3fec73648ce02831927bf3ff656d359c06ac367d7a6420080df0f557aee4
|
3 |
+
size 14663
|