End of training
Browse files- checkpoint-34000/optimizer.bin +3 -0
- checkpoint-34000/random_states_0.pkl +3 -0
- checkpoint-34000/scaler.pt +3 -0
- checkpoint-34000/scheduler.bin +3 -0
- checkpoint-34000/unet/config.json +56 -0
- checkpoint-34000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-34000/unet_ema/config.json +63 -0
- checkpoint-34000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-36000/optimizer.bin +3 -0
- checkpoint-36000/random_states_0.pkl +3 -0
- checkpoint-36000/scaler.pt +3 -0
- checkpoint-36000/scheduler.bin +3 -0
- checkpoint-36000/unet/config.json +56 -0
- checkpoint-36000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-36000/unet_ema/config.json +63 -0
- checkpoint-36000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-38000/optimizer.bin +3 -0
- checkpoint-38000/random_states_0.pkl +3 -0
- checkpoint-38000/scaler.pt +3 -0
- checkpoint-38000/scheduler.bin +3 -0
- checkpoint-38000/unet/config.json +56 -0
- checkpoint-38000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-38000/unet_ema/config.json +63 -0
- checkpoint-38000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-40000/optimizer.bin +3 -0
- checkpoint-40000/random_states_0.pkl +3 -0
- checkpoint-40000/scaler.pt +3 -0
- checkpoint-40000/scheduler.bin +3 -0
- checkpoint-40000/unet/config.json +56 -0
- checkpoint-40000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-40000/unet_ema/config.json +63 -0
- checkpoint-40000/unet_ema/diffusion_pytorch_model.bin +3 -0
- model_index.json +33 -0
- scheduler/scheduler_config.json +18 -0
- text_encoder/config.json +25 -0
- text_encoder/pytorch_model.bin +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +24 -0
- tokenizer/tokenizer_config.json +33 -0
- tokenizer/vocab.json +0 -0
- unet/config.json +56 -0
- unet/diffusion_pytorch_model.bin +3 -0
- vae/config.json +31 -0
- vae/diffusion_pytorch_model.bin +3 -0
checkpoint-34000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b9be6d768a0235822ae8ba528c99ebc07a6d8b4dc5597f063daed3b6ce47a67
|
3 |
+
size 6876749403
|
checkpoint-34000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38d6ab5e423659210ff31bb0fe6cbe27fb5e3bc76ec62564c1f92b2046d5b8a2
|
3 |
+
size 14663
|
checkpoint-34000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c6ed14a6fd48130155374aeb3da88fc94f6251f08b94f6ec42e73ca0375e30e
|
3 |
+
size 557
|
checkpoint-34000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f341a570dd72cf76d44337000a111b05738d4ebe08dc37936699163d9b43b85
|
3 |
+
size 563
|
checkpoint-34000/unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"_name_or_path": "dreamlike-art/dreamlike-photoreal-2.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280,
|
11 |
+
1280
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"class_embed_type": null,
|
15 |
+
"class_embeddings_concat": false,
|
16 |
+
"conv_in_kernel": 3,
|
17 |
+
"conv_out_kernel": 3,
|
18 |
+
"cross_attention_dim": 768,
|
19 |
+
"down_block_types": [
|
20 |
+
"CrossAttnDownBlock2D",
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"DownBlock2D"
|
24 |
+
],
|
25 |
+
"downsample_padding": 1,
|
26 |
+
"dual_cross_attention": false,
|
27 |
+
"encoder_hid_dim": null,
|
28 |
+
"flip_sin_to_cos": true,
|
29 |
+
"freq_shift": 0,
|
30 |
+
"in_channels": 4,
|
31 |
+
"layers_per_block": 2,
|
32 |
+
"mid_block_only_cross_attention": null,
|
33 |
+
"mid_block_scale_factor": 1,
|
34 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
35 |
+
"norm_eps": 1e-05,
|
36 |
+
"norm_num_groups": 32,
|
37 |
+
"num_class_embeds": null,
|
38 |
+
"only_cross_attention": false,
|
39 |
+
"out_channels": 4,
|
40 |
+
"projection_class_embeddings_input_dim": null,
|
41 |
+
"resnet_out_scale_factor": 1.0,
|
42 |
+
"resnet_skip_time_act": false,
|
43 |
+
"resnet_time_scale_shift": "default",
|
44 |
+
"sample_size": 96,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_type": "positional",
|
47 |
+
"timestep_post_act": null,
|
48 |
+
"up_block_types": [
|
49 |
+
"UpBlock2D",
|
50 |
+
"CrossAttnUpBlock2D",
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"CrossAttnUpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
checkpoint-34000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9108aeb571b0f46ca7199ef8bb923ea3402da10c176a026bd406d523c928cecd
|
3 |
+
size 3438375973
|
checkpoint-34000/unet_ema/config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"_name_or_path": "dreamlike-art/dreamlike-photoreal-2.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280,
|
11 |
+
1280
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"class_embed_type": null,
|
15 |
+
"class_embeddings_concat": false,
|
16 |
+
"conv_in_kernel": 3,
|
17 |
+
"conv_out_kernel": 3,
|
18 |
+
"cross_attention_dim": 768,
|
19 |
+
"decay": 0.9999,
|
20 |
+
"down_block_types": [
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"CrossAttnDownBlock2D",
|
24 |
+
"DownBlock2D"
|
25 |
+
],
|
26 |
+
"downsample_padding": 1,
|
27 |
+
"dual_cross_attention": false,
|
28 |
+
"encoder_hid_dim": null,
|
29 |
+
"flip_sin_to_cos": true,
|
30 |
+
"freq_shift": 0,
|
31 |
+
"in_channels": 4,
|
32 |
+
"inv_gamma": 1.0,
|
33 |
+
"layers_per_block": 2,
|
34 |
+
"mid_block_only_cross_attention": null,
|
35 |
+
"mid_block_scale_factor": 1,
|
36 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
37 |
+
"min_decay": 0.0,
|
38 |
+
"norm_eps": 1e-05,
|
39 |
+
"norm_num_groups": 32,
|
40 |
+
"num_class_embeds": null,
|
41 |
+
"only_cross_attention": false,
|
42 |
+
"optimization_step": 34000,
|
43 |
+
"out_channels": 4,
|
44 |
+
"power": 0.6666666666666666,
|
45 |
+
"projection_class_embeddings_input_dim": null,
|
46 |
+
"resnet_out_scale_factor": 1.0,
|
47 |
+
"resnet_skip_time_act": false,
|
48 |
+
"resnet_time_scale_shift": "default",
|
49 |
+
"sample_size": 96,
|
50 |
+
"time_cond_proj_dim": null,
|
51 |
+
"time_embedding_type": "positional",
|
52 |
+
"timestep_post_act": null,
|
53 |
+
"up_block_types": [
|
54 |
+
"UpBlock2D",
|
55 |
+
"CrossAttnUpBlock2D",
|
56 |
+
"CrossAttnUpBlock2D",
|
57 |
+
"CrossAttnUpBlock2D"
|
58 |
+
],
|
59 |
+
"upcast_attention": false,
|
60 |
+
"update_after_step": 0,
|
61 |
+
"use_ema_warmup": false,
|
62 |
+
"use_linear_projection": false
|
63 |
+
}
|
checkpoint-34000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2196a3cfae17718135fca9a1669e727ef39b629d490d1df96961c5e9883d3ef8
|
3 |
+
size 3438366373
|
checkpoint-36000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e05e296a8fc71f587932639d3ffdcf8d1137ca0e80e1c8f59ac4e942fde469d8
|
3 |
+
size 6876749403
|
checkpoint-36000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31be817c9e59722c89d5a73b4ec15c0a464d09bb2ac73a4adb0c3ea51b2a9952
|
3 |
+
size 14663
|
checkpoint-36000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7728dd0433bd52fe83933468b8bde0b2af7621d234d53762f56906179589895d
|
3 |
+
size 557
|
checkpoint-36000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0c0d6ad2f9bd97900d9b94f60433a0aa593acface70e0eec976d9f2244c43a1
|
3 |
+
size 563
|
checkpoint-36000/unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"_name_or_path": "ArchSynthesis_v2/checkpoint-34000",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280,
|
11 |
+
1280
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"class_embed_type": null,
|
15 |
+
"class_embeddings_concat": false,
|
16 |
+
"conv_in_kernel": 3,
|
17 |
+
"conv_out_kernel": 3,
|
18 |
+
"cross_attention_dim": 768,
|
19 |
+
"down_block_types": [
|
20 |
+
"CrossAttnDownBlock2D",
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"DownBlock2D"
|
24 |
+
],
|
25 |
+
"downsample_padding": 1,
|
26 |
+
"dual_cross_attention": false,
|
27 |
+
"encoder_hid_dim": null,
|
28 |
+
"flip_sin_to_cos": true,
|
29 |
+
"freq_shift": 0,
|
30 |
+
"in_channels": 4,
|
31 |
+
"layers_per_block": 2,
|
32 |
+
"mid_block_only_cross_attention": null,
|
33 |
+
"mid_block_scale_factor": 1,
|
34 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
35 |
+
"norm_eps": 1e-05,
|
36 |
+
"norm_num_groups": 32,
|
37 |
+
"num_class_embeds": null,
|
38 |
+
"only_cross_attention": false,
|
39 |
+
"out_channels": 4,
|
40 |
+
"projection_class_embeddings_input_dim": null,
|
41 |
+
"resnet_out_scale_factor": 1.0,
|
42 |
+
"resnet_skip_time_act": false,
|
43 |
+
"resnet_time_scale_shift": "default",
|
44 |
+
"sample_size": 96,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_type": "positional",
|
47 |
+
"timestep_post_act": null,
|
48 |
+
"up_block_types": [
|
49 |
+
"UpBlock2D",
|
50 |
+
"CrossAttnUpBlock2D",
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"CrossAttnUpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
checkpoint-36000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8a84d5da0917ad4bc5656230f869c9387c368194bc5f7b5ddd4edfa099ce386
|
3 |
+
size 3438375973
|
checkpoint-36000/unet_ema/config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"_name_or_path": "dreamlike-art/dreamlike-photoreal-2.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280,
|
11 |
+
1280
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"class_embed_type": null,
|
15 |
+
"class_embeddings_concat": false,
|
16 |
+
"conv_in_kernel": 3,
|
17 |
+
"conv_out_kernel": 3,
|
18 |
+
"cross_attention_dim": 768,
|
19 |
+
"decay": 0.9999,
|
20 |
+
"down_block_types": [
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"CrossAttnDownBlock2D",
|
24 |
+
"DownBlock2D"
|
25 |
+
],
|
26 |
+
"downsample_padding": 1,
|
27 |
+
"dual_cross_attention": false,
|
28 |
+
"encoder_hid_dim": null,
|
29 |
+
"flip_sin_to_cos": true,
|
30 |
+
"freq_shift": 0,
|
31 |
+
"in_channels": 4,
|
32 |
+
"inv_gamma": 1.0,
|
33 |
+
"layers_per_block": 2,
|
34 |
+
"mid_block_only_cross_attention": null,
|
35 |
+
"mid_block_scale_factor": 1,
|
36 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
37 |
+
"min_decay": 0.0,
|
38 |
+
"norm_eps": 1e-05,
|
39 |
+
"norm_num_groups": 32,
|
40 |
+
"num_class_embeds": null,
|
41 |
+
"only_cross_attention": false,
|
42 |
+
"optimization_step": 2000,
|
43 |
+
"out_channels": 4,
|
44 |
+
"power": 0.6666666666666666,
|
45 |
+
"projection_class_embeddings_input_dim": null,
|
46 |
+
"resnet_out_scale_factor": 1.0,
|
47 |
+
"resnet_skip_time_act": false,
|
48 |
+
"resnet_time_scale_shift": "default",
|
49 |
+
"sample_size": 96,
|
50 |
+
"time_cond_proj_dim": null,
|
51 |
+
"time_embedding_type": "positional",
|
52 |
+
"timestep_post_act": null,
|
53 |
+
"up_block_types": [
|
54 |
+
"UpBlock2D",
|
55 |
+
"CrossAttnUpBlock2D",
|
56 |
+
"CrossAttnUpBlock2D",
|
57 |
+
"CrossAttnUpBlock2D"
|
58 |
+
],
|
59 |
+
"upcast_attention": false,
|
60 |
+
"update_after_step": 0,
|
61 |
+
"use_ema_warmup": false,
|
62 |
+
"use_linear_projection": false
|
63 |
+
}
|
checkpoint-36000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6204bf34fc2d64e9ed426557fa863e6b0864c33219c372df3d4a647ab99c3e0e
|
3 |
+
size 3438366373
|
checkpoint-38000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:388f0d4b0368e6a1b1b485f40b12be6f7cc24c76ee0f5d4d8ba0a2dee73cad72
|
3 |
+
size 6876749403
|
checkpoint-38000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73781037ddf189a25954d5d2df03cf4cbf13b59c577c4ea53eab8c7ef8e6f0ff
|
3 |
+
size 14663
|
checkpoint-38000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b415639e39ec97e7d2a2b3aa82012619b036bcb9a48106bdf820005e7a5f5b6
|
3 |
+
size 557
|
checkpoint-38000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:021a99951e96e2cb4a2c0411bdf2867ed45c7d94bd9cc13955667d1fba6a8589
|
3 |
+
size 563
|
checkpoint-38000/unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"_name_or_path": "ArchSynthesis_v2/checkpoint-34000",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280,
|
11 |
+
1280
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"class_embed_type": null,
|
15 |
+
"class_embeddings_concat": false,
|
16 |
+
"conv_in_kernel": 3,
|
17 |
+
"conv_out_kernel": 3,
|
18 |
+
"cross_attention_dim": 768,
|
19 |
+
"down_block_types": [
|
20 |
+
"CrossAttnDownBlock2D",
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"DownBlock2D"
|
24 |
+
],
|
25 |
+
"downsample_padding": 1,
|
26 |
+
"dual_cross_attention": false,
|
27 |
+
"encoder_hid_dim": null,
|
28 |
+
"flip_sin_to_cos": true,
|
29 |
+
"freq_shift": 0,
|
30 |
+
"in_channels": 4,
|
31 |
+
"layers_per_block": 2,
|
32 |
+
"mid_block_only_cross_attention": null,
|
33 |
+
"mid_block_scale_factor": 1,
|
34 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
35 |
+
"norm_eps": 1e-05,
|
36 |
+
"norm_num_groups": 32,
|
37 |
+
"num_class_embeds": null,
|
38 |
+
"only_cross_attention": false,
|
39 |
+
"out_channels": 4,
|
40 |
+
"projection_class_embeddings_input_dim": null,
|
41 |
+
"resnet_out_scale_factor": 1.0,
|
42 |
+
"resnet_skip_time_act": false,
|
43 |
+
"resnet_time_scale_shift": "default",
|
44 |
+
"sample_size": 96,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_type": "positional",
|
47 |
+
"timestep_post_act": null,
|
48 |
+
"up_block_types": [
|
49 |
+
"UpBlock2D",
|
50 |
+
"CrossAttnUpBlock2D",
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"CrossAttnUpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
checkpoint-38000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8b474881c487ba7ba849d3a3719ee682c79b6479c64dd5631577fada90c75af
|
3 |
+
size 3438375973
|
checkpoint-38000/unet_ema/config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"_name_or_path": "dreamlike-art/dreamlike-photoreal-2.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280,
|
11 |
+
1280
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"class_embed_type": null,
|
15 |
+
"class_embeddings_concat": false,
|
16 |
+
"conv_in_kernel": 3,
|
17 |
+
"conv_out_kernel": 3,
|
18 |
+
"cross_attention_dim": 768,
|
19 |
+
"decay": 0.9999,
|
20 |
+
"down_block_types": [
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"CrossAttnDownBlock2D",
|
24 |
+
"DownBlock2D"
|
25 |
+
],
|
26 |
+
"downsample_padding": 1,
|
27 |
+
"dual_cross_attention": false,
|
28 |
+
"encoder_hid_dim": null,
|
29 |
+
"flip_sin_to_cos": true,
|
30 |
+
"freq_shift": 0,
|
31 |
+
"in_channels": 4,
|
32 |
+
"inv_gamma": 1.0,
|
33 |
+
"layers_per_block": 2,
|
34 |
+
"mid_block_only_cross_attention": null,
|
35 |
+
"mid_block_scale_factor": 1,
|
36 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
37 |
+
"min_decay": 0.0,
|
38 |
+
"norm_eps": 1e-05,
|
39 |
+
"norm_num_groups": 32,
|
40 |
+
"num_class_embeds": null,
|
41 |
+
"only_cross_attention": false,
|
42 |
+
"optimization_step": 4000,
|
43 |
+
"out_channels": 4,
|
44 |
+
"power": 0.6666666666666666,
|
45 |
+
"projection_class_embeddings_input_dim": null,
|
46 |
+
"resnet_out_scale_factor": 1.0,
|
47 |
+
"resnet_skip_time_act": false,
|
48 |
+
"resnet_time_scale_shift": "default",
|
49 |
+
"sample_size": 96,
|
50 |
+
"time_cond_proj_dim": null,
|
51 |
+
"time_embedding_type": "positional",
|
52 |
+
"timestep_post_act": null,
|
53 |
+
"up_block_types": [
|
54 |
+
"UpBlock2D",
|
55 |
+
"CrossAttnUpBlock2D",
|
56 |
+
"CrossAttnUpBlock2D",
|
57 |
+
"CrossAttnUpBlock2D"
|
58 |
+
],
|
59 |
+
"upcast_attention": false,
|
60 |
+
"update_after_step": 0,
|
61 |
+
"use_ema_warmup": false,
|
62 |
+
"use_linear_projection": false
|
63 |
+
}
|
checkpoint-38000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76f76b3d42a70cb823cccc56d8089d9f0b3718879e2c02078f9c911e42ec139b
|
3 |
+
size 3438366373
|
checkpoint-40000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17c7eadbe4eb7f2d966026af34bfcdb18cbe5a12f02c42545a81970baaaa6f49
|
3 |
+
size 6876749403
|
checkpoint-40000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1867694cebf71b09a52031f4c607d271e8f11683ae1089f06a6a2b258c753c5
|
3 |
+
size 14663
|
checkpoint-40000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b378fab10a2de34b682946ef834496f56a6d743140d59753e51b8e0f0291c944
|
3 |
+
size 557
|
checkpoint-40000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a71e390a3842b97762119c51f2bc5c9ffd08704699e96851ebb8455dd707551
|
3 |
+
size 563
|
checkpoint-40000/unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"_name_or_path": "ArchSynthesis_v2/checkpoint-34000",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280,
|
11 |
+
1280
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"class_embed_type": null,
|
15 |
+
"class_embeddings_concat": false,
|
16 |
+
"conv_in_kernel": 3,
|
17 |
+
"conv_out_kernel": 3,
|
18 |
+
"cross_attention_dim": 768,
|
19 |
+
"down_block_types": [
|
20 |
+
"CrossAttnDownBlock2D",
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"DownBlock2D"
|
24 |
+
],
|
25 |
+
"downsample_padding": 1,
|
26 |
+
"dual_cross_attention": false,
|
27 |
+
"encoder_hid_dim": null,
|
28 |
+
"flip_sin_to_cos": true,
|
29 |
+
"freq_shift": 0,
|
30 |
+
"in_channels": 4,
|
31 |
+
"layers_per_block": 2,
|
32 |
+
"mid_block_only_cross_attention": null,
|
33 |
+
"mid_block_scale_factor": 1,
|
34 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
35 |
+
"norm_eps": 1e-05,
|
36 |
+
"norm_num_groups": 32,
|
37 |
+
"num_class_embeds": null,
|
38 |
+
"only_cross_attention": false,
|
39 |
+
"out_channels": 4,
|
40 |
+
"projection_class_embeddings_input_dim": null,
|
41 |
+
"resnet_out_scale_factor": 1.0,
|
42 |
+
"resnet_skip_time_act": false,
|
43 |
+
"resnet_time_scale_shift": "default",
|
44 |
+
"sample_size": 96,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_type": "positional",
|
47 |
+
"timestep_post_act": null,
|
48 |
+
"up_block_types": [
|
49 |
+
"UpBlock2D",
|
50 |
+
"CrossAttnUpBlock2D",
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"CrossAttnUpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
checkpoint-40000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a5eae02559644b2879ce9f50437cff5fb8f826f63832f3e5f5d14d9bf4fcd9d
|
3 |
+
size 3438375973
|
checkpoint-40000/unet_ema/config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"_name_or_path": "dreamlike-art/dreamlike-photoreal-2.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280,
|
11 |
+
1280
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"class_embed_type": null,
|
15 |
+
"class_embeddings_concat": false,
|
16 |
+
"conv_in_kernel": 3,
|
17 |
+
"conv_out_kernel": 3,
|
18 |
+
"cross_attention_dim": 768,
|
19 |
+
"decay": 0.9999,
|
20 |
+
"down_block_types": [
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"CrossAttnDownBlock2D",
|
24 |
+
"DownBlock2D"
|
25 |
+
],
|
26 |
+
"downsample_padding": 1,
|
27 |
+
"dual_cross_attention": false,
|
28 |
+
"encoder_hid_dim": null,
|
29 |
+
"flip_sin_to_cos": true,
|
30 |
+
"freq_shift": 0,
|
31 |
+
"in_channels": 4,
|
32 |
+
"inv_gamma": 1.0,
|
33 |
+
"layers_per_block": 2,
|
34 |
+
"mid_block_only_cross_attention": null,
|
35 |
+
"mid_block_scale_factor": 1,
|
36 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
37 |
+
"min_decay": 0.0,
|
38 |
+
"norm_eps": 1e-05,
|
39 |
+
"norm_num_groups": 32,
|
40 |
+
"num_class_embeds": null,
|
41 |
+
"only_cross_attention": false,
|
42 |
+
"optimization_step": 6000,
|
43 |
+
"out_channels": 4,
|
44 |
+
"power": 0.6666666666666666,
|
45 |
+
"projection_class_embeddings_input_dim": null,
|
46 |
+
"resnet_out_scale_factor": 1.0,
|
47 |
+
"resnet_skip_time_act": false,
|
48 |
+
"resnet_time_scale_shift": "default",
|
49 |
+
"sample_size": 96,
|
50 |
+
"time_cond_proj_dim": null,
|
51 |
+
"time_embedding_type": "positional",
|
52 |
+
"timestep_post_act": null,
|
53 |
+
"up_block_types": [
|
54 |
+
"UpBlock2D",
|
55 |
+
"CrossAttnUpBlock2D",
|
56 |
+
"CrossAttnUpBlock2D",
|
57 |
+
"CrossAttnUpBlock2D"
|
58 |
+
],
|
59 |
+
"upcast_attention": false,
|
60 |
+
"update_after_step": 0,
|
61 |
+
"use_ema_warmup": false,
|
62 |
+
"use_linear_projection": false
|
63 |
+
}
|
checkpoint-40000/unet_ema/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72da89c993edaa53a166a83f786aa5d4897a804e94c9c4190134b11b10012002
|
3 |
+
size 3438366373
|
model_index.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
null,
|
6 |
+
null
|
7 |
+
],
|
8 |
+
"requires_safety_checker": null,
|
9 |
+
"safety_checker": [
|
10 |
+
null,
|
11 |
+
null
|
12 |
+
],
|
13 |
+
"scheduler": [
|
14 |
+
"diffusers",
|
15 |
+
"DDIMScheduler"
|
16 |
+
],
|
17 |
+
"text_encoder": [
|
18 |
+
"transformers",
|
19 |
+
"CLIPTextModel"
|
20 |
+
],
|
21 |
+
"tokenizer": [
|
22 |
+
"transformers",
|
23 |
+
"CLIPTokenizer"
|
24 |
+
],
|
25 |
+
"unet": [
|
26 |
+
"diffusers",
|
27 |
+
"UNet2DConditionModel"
|
28 |
+
],
|
29 |
+
"vae": [
|
30 |
+
"diffusers",
|
31 |
+
"AutoencoderKL"
|
32 |
+
]
|
33 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDIMScheduler",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"beta_end": 0.012,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.00085,
|
7 |
+
"clip_sample": false,
|
8 |
+
"clip_sample_range": 1.0,
|
9 |
+
"dynamic_thresholding_ratio": 0.995,
|
10 |
+
"num_train_timesteps": 1000,
|
11 |
+
"prediction_type": "epsilon",
|
12 |
+
"sample_max_value": 1.0,
|
13 |
+
"set_alpha_to_one": false,
|
14 |
+
"skip_prk_steps": true,
|
15 |
+
"steps_offset": 1,
|
16 |
+
"thresholding": false,
|
17 |
+
"trained_betas": null
|
18 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dreamlike-art/dreamlike-photoreal-2.0",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextModel"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"dropout": 0.0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "quick_gelu",
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 768,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.27.4",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ab754067ad03cb25a851efd84d6843756b5182df2da870d73e3173d190114ef
|
3 |
+
size 246188833
|
tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<|startoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"do_lower_case": true,
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"model_max_length": 77,
|
22 |
+
"pad_token": "<|endoftext|>",
|
23 |
+
"special_tokens_map_file": "./special_tokens_map.json",
|
24 |
+
"tokenizer_class": "CLIPTokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<|endoftext|>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"_name_or_path": "ArchSynthesis_v2/checkpoint-34000",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280,
|
11 |
+
1280
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"class_embed_type": null,
|
15 |
+
"class_embeddings_concat": false,
|
16 |
+
"conv_in_kernel": 3,
|
17 |
+
"conv_out_kernel": 3,
|
18 |
+
"cross_attention_dim": 768,
|
19 |
+
"down_block_types": [
|
20 |
+
"CrossAttnDownBlock2D",
|
21 |
+
"CrossAttnDownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D",
|
23 |
+
"DownBlock2D"
|
24 |
+
],
|
25 |
+
"downsample_padding": 1,
|
26 |
+
"dual_cross_attention": false,
|
27 |
+
"encoder_hid_dim": null,
|
28 |
+
"flip_sin_to_cos": true,
|
29 |
+
"freq_shift": 0,
|
30 |
+
"in_channels": 4,
|
31 |
+
"layers_per_block": 2,
|
32 |
+
"mid_block_only_cross_attention": null,
|
33 |
+
"mid_block_scale_factor": 1,
|
34 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
35 |
+
"norm_eps": 1e-05,
|
36 |
+
"norm_num_groups": 32,
|
37 |
+
"num_class_embeds": null,
|
38 |
+
"only_cross_attention": false,
|
39 |
+
"out_channels": 4,
|
40 |
+
"projection_class_embeddings_input_dim": null,
|
41 |
+
"resnet_out_scale_factor": 1.0,
|
42 |
+
"resnet_skip_time_act": false,
|
43 |
+
"resnet_time_scale_shift": "default",
|
44 |
+
"sample_size": 96,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_type": "positional",
|
47 |
+
"timestep_post_act": null,
|
48 |
+
"up_block_types": [
|
49 |
+
"UpBlock2D",
|
50 |
+
"CrossAttnUpBlock2D",
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"CrossAttnUpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f79d8e83e780eada8466044433c83842ac50a3642a5d66e5564c825eea8877fe
|
3 |
+
size 3438375973
|
vae/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"_name_or_path": "dreamlike-art/dreamlike-photoreal-2.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"block_out_channels": [
|
7 |
+
128,
|
8 |
+
256,
|
9 |
+
512,
|
10 |
+
512
|
11 |
+
],
|
12 |
+
"down_block_types": [
|
13 |
+
"DownEncoderBlock2D",
|
14 |
+
"DownEncoderBlock2D",
|
15 |
+
"DownEncoderBlock2D",
|
16 |
+
"DownEncoderBlock2D"
|
17 |
+
],
|
18 |
+
"in_channels": 3,
|
19 |
+
"latent_channels": 4,
|
20 |
+
"layers_per_block": 2,
|
21 |
+
"norm_num_groups": 32,
|
22 |
+
"out_channels": 3,
|
23 |
+
"sample_size": 256,
|
24 |
+
"scaling_factor": 0.18215,
|
25 |
+
"up_block_types": [
|
26 |
+
"UpDecoderBlock2D",
|
27 |
+
"UpDecoderBlock2D",
|
28 |
+
"UpDecoderBlock2D",
|
29 |
+
"UpDecoderBlock2D"
|
30 |
+
]
|
31 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:279af4d9c9aff6b409cb4069aa1e522251024516c3b514065ab130182ca45f11
|
3 |
+
size 167407601
|