Epoch 5
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-17500/optimizer.bin +3 -0
- checkpoint-17500/random_states_0.pkl +3 -0
- checkpoint-17500/scaler.pt +3 -0
- checkpoint-17500/scheduler.bin +3 -0
- checkpoint-17500/unet/config.json +60 -0
- checkpoint-17500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-17500/unet_ema/config.json +67 -0
- checkpoint-17500/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-18000/optimizer.bin +3 -0
- checkpoint-18000/random_states_0.pkl +3 -0
- checkpoint-18000/scaler.pt +3 -0
- checkpoint-18000/scheduler.bin +3 -0
- checkpoint-18000/unet/config.json +60 -0
- checkpoint-18000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-18000/unet_ema/config.json +67 -0
- checkpoint-18000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-18500/optimizer.bin +3 -0
- checkpoint-18500/random_states_0.pkl +3 -0
- checkpoint-18500/scaler.pt +3 -0
- checkpoint-18500/scheduler.bin +3 -0
- checkpoint-18500/unet/config.json +60 -0
- checkpoint-18500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-18500/unet_ema/config.json +67 -0
- checkpoint-18500/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-19000/optimizer.bin +3 -0
- checkpoint-19000/random_states_0.pkl +3 -0
- checkpoint-19000/scaler.pt +3 -0
- checkpoint-19000/scheduler.bin +3 -0
- checkpoint-19000/unet/config.json +60 -0
- checkpoint-19000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-19000/unet_ema/config.json +67 -0
- checkpoint-19000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-19500/optimizer.bin +3 -0
- checkpoint-19500/random_states_0.pkl +3 -0
- checkpoint-19500/scaler.pt +3 -0
- checkpoint-19500/scheduler.bin +3 -0
- checkpoint-19500/unet/config.json +60 -0
- checkpoint-19500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-19500/unet_ema/config.json +67 -0
- checkpoint-19500/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-20000/optimizer.bin +3 -0
- checkpoint-20000/random_states_0.pkl +3 -0
- checkpoint-20000/scaler.pt +3 -0
- checkpoint-20000/scheduler.bin +3 -0
- checkpoint-20000/unet/config.json +60 -0
- checkpoint-20000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-20000/unet_ema/config.json +67 -0
- checkpoint-20000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-20500/optimizer.bin +3 -0
- checkpoint-20500/random_states_0.pkl +3 -0
checkpoint-17500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d820846eaf1b2740fd817d251c0ea37d9a852eb7871107807ef32d50508aa438
|
3 |
+
size 73251413
|
checkpoint-17500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e54d0a698d4431b7212ddaa7064213dcf6d8aecb7cffd716a80427b37ff40197
|
3 |
+
size 14663
|
checkpoint-17500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9400f0b95faf8c01a9e1ba8949f06a7d0a0504bb7f752fe6cebd672f22cd6fd0
|
3 |
+
size 557
|
checkpoint-17500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52648a1268bd0036b559d9681291fb045e1ed0b6cabc76d556332b3b192ad1ce
|
3 |
+
size 563
|
checkpoint-17500/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-17500/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08e1b6f0893ea039e25fb885e70bd5a244b8461427cce9f7d71a644c7f897b16
|
3 |
+
size 36621969
|
checkpoint-17500/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": 17500,
|
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-17500/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc05948ba73bc72a0588719bd758af1709d45d55364bd7dbc4137e4c7291c55e
|
3 |
+
size 36616081
|
checkpoint-18000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d0a1efde1cc579dd97308e9b0f629d58a0f33c8cd4f8f83d0707b6ada74c3b1
|
3 |
+
size 73251413
|
checkpoint-18000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7550bc227cc0c929cd1f3d5f0531a4686d8612fbdedc34d92b99035a386941d
|
3 |
+
size 14663
|
checkpoint-18000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50f582cf868be70e3f6a0e759b344c11df99721dccd9a233e0b2db952578e9eb
|
3 |
+
size 557
|
checkpoint-18000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e357e09d419513829367eeae80e71d01b233f962bcc5fce2a7ad0de9d2d8d20
|
3 |
+
size 563
|
checkpoint-18000/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-18000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d8904e435c41b303cf46bb8da206d3fd682ac0f45f61a39bad9733cff6f935b
|
3 |
+
size 36621969
|
checkpoint-18000/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": 18000,
|
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-18000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dd9d0c9749b7479e9977bd7ad8256e695d8425a39d5125c93487c9242dc02d0
|
3 |
+
size 36616081
|
checkpoint-18500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3591741e75af49d0194212a9f53212120616bbe852e6e57a790c2a81f5ceb73e
|
3 |
+
size 73251413
|
checkpoint-18500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4ba440e488010881116912e35fc8d4ff6c38348c41d4b688cc43f2173c18adf
|
3 |
+
size 14663
|
checkpoint-18500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03fc7fc2b2e161278bf7ff2a8586dbcabad84d9740e5a17339b41e6c13526262
|
3 |
+
size 557
|
checkpoint-18500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8560f326171665c0ab2c4a927ed376e68167e1e009bc6b35de2c9b9e4ad96f12
|
3 |
+
size 563
|
checkpoint-18500/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-18500/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4b4f6bde2a77073548bcbb8af5d55d163a6cad235725b87d31a3c2570e47a07
|
3 |
+
size 36621969
|
checkpoint-18500/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": 18500,
|
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-18500/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43d2dbf3321efa88789967ac3ad8120ab9d1ea7d928b209044589f8d39a8df99
|
3 |
+
size 36616081
|
checkpoint-19000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f235e0845796b4928137e8ea221d1ba8a2c977eb0c7d2a3b4098ca960b37ba7a
|
3 |
+
size 73251413
|
checkpoint-19000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b058058cb213b7440a866f7546f955fd70aebc98b1433d9d462a737ea908348c
|
3 |
+
size 14663
|
checkpoint-19000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e9d7f79ff2afbc7f7732f986f8b048655b231e198ac0d90be5a4c0ff3168c79
|
3 |
+
size 557
|
checkpoint-19000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac28b9e8474d01117d7bd59860b3db2d56cfa0f3a96522943c6036f3ec6ae7cb
|
3 |
+
size 563
|
checkpoint-19000/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-19000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99d045113191cbc8dc1c70c3d8251b99152a5182ac3b7fb4aed5bea1accb26f4
|
3 |
+
size 36621969
|
checkpoint-19000/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": 19000,
|
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-19000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b3d5f0edc8cb667f131cebe984de1b34a19b25a3a4a9ff1aac20aba71010e98
|
3 |
+
size 36616081
|
checkpoint-19500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c7b2b790b3efd16b3a6dd09eb0cd8193f2ea3a9745cc6df3bf6aea5dfa5c975
|
3 |
+
size 73251413
|
checkpoint-19500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d690d7d1055b3aaad232ed9af5febe8d74bd71f65bf2a02a9f0eefb99eb99e7f
|
3 |
+
size 14663
|
checkpoint-19500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df12d68ca2081a0ca38ec56f693327916d844c40ce2ce6f3fe1378ef97699d01
|
3 |
+
size 557
|
checkpoint-19500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5674017e3d1d0d46706078639c74cfff1b49b96b6583896c8affeb9719c3b01e
|
3 |
+
size 563
|
checkpoint-19500/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-19500/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d855dea1453c5265c9d27afd2e914a07dc1e6b9e6cc465c8934134e11c3cc7b
|
3 |
+
size 36621969
|
checkpoint-19500/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": 19500,
|
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-19500/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75d3e3ff3caaf94d05cd54e3008d6b2d66bb8795ae5f8bf90d9057301841b0aa
|
3 |
+
size 36616081
|
checkpoint-20000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b437f0ce24388d431bfcb8140cdebba1b2c8d046515669100deb35b550ed20a6
|
3 |
+
size 73251413
|
checkpoint-20000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:178849f5690dc5dd51e61d9497c02242da5a86bfff07d5f64c34fa3534be2f33
|
3 |
+
size 14663
|
checkpoint-20000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44247269161fd2d1f375294868924f890586b8627b2fe0e14f821b2a461ce2d7
|
3 |
+
size 557
|
checkpoint-20000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee07afe8a331711deac55b8bfe5f46519f5eaa686b271a807aeb1bec46c32dd4
|
3 |
+
size 563
|
checkpoint-20000/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-20000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8769d323a3a8f71af779a72a60ef3e612be8676dcd0a176587f7836de1d4e291
|
3 |
+
size 36621969
|
checkpoint-20000/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": 20000,
|
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-20000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e44c5f24359ad7a6c33e1da269bc7a80815d66337e7f5cd6628aa4ec328c2f50
|
3 |
+
size 36616081
|
checkpoint-20500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:258bcf6a16aa965105087fc2824e4d8aff285aa68e974143145e32a242bdef27
|
3 |
+
size 73251413
|
checkpoint-20500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88e182d178bed7de9f7d3dd6ffc020cb1addde0006375f121dba50e08518fe62
|
3 |
+
size 14663
|