Upload folder using huggingface_hub
#1
by
xarthurx
- opened
This view is limited to 50 files because it contains too many changes.
See the raw diff here.
- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-1000/text_encoder/config.json +25 -0
- checkpoint-1000/text_encoder/pytorch_model.bin +3 -0
- checkpoint-1000/unet/config.json +66 -0
- checkpoint-1000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-2000/optimizer.bin +3 -0
- checkpoint-2000/random_states_0.pkl +3 -0
- checkpoint-2000/scaler.pt +3 -0
- checkpoint-2000/scheduler.bin +3 -0
- checkpoint-2000/text_encoder/config.json +25 -0
- checkpoint-2000/text_encoder/pytorch_model.bin +3 -0
- checkpoint-2000/unet/config.json +66 -0
- checkpoint-2000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-3000/optimizer.bin +3 -0
- checkpoint-3000/random_states_0.pkl +3 -0
- checkpoint-3000/scaler.pt +3 -0
- checkpoint-3000/scheduler.bin +3 -0
- checkpoint-3000/text_encoder/config.json +25 -0
- checkpoint-3000/text_encoder/pytorch_model.bin +3 -0
- checkpoint-3000/unet/config.json +66 -0
- checkpoint-3000/unet/diffusion_pytorch_model.bin +3 -0
- feature_extractor/preprocessor_config.json +28 -0
- logs/dreambooth/1684134445.407711/events.out.tfevents.1684134445.3144edec4884.691.1 +3 -0
- logs/dreambooth/1684134445.4103186/hparams.yml +52 -0
- logs/dreambooth/1684134521.9282608/events.out.tfevents.1684134521.3144edec4884.742.1 +3 -0
- logs/dreambooth/1684134521.9308062/hparams.yml +52 -0
- logs/dreambooth/1684134566.1052556/events.out.tfevents.1684134566.3144edec4884.780.1 +3 -0
- logs/dreambooth/1684134566.1079392/hparams.yml +52 -0
- logs/dreambooth/1684134653.766244/events.out.tfevents.1684134653.3144edec4884.823.1 +3 -0
- logs/dreambooth/1684134653.7687936/hparams.yml +52 -0
- logs/dreambooth/1684134713.7159472/events.out.tfevents.1684134713.3144edec4884.864.1 +3 -0
- logs/dreambooth/1684134713.7184079/hparams.yml +52 -0
- logs/dreambooth/events.out.tfevents.1684134445.3144edec4884.691.0 +3 -0
- logs/dreambooth/events.out.tfevents.1684134521.3144edec4884.742.0 +3 -0
- logs/dreambooth/events.out.tfevents.1684134566.3144edec4884.780.0 +3 -0
- logs/dreambooth/events.out.tfevents.1684134653.3144edec4884.823.0 +3 -0
- logs/dreambooth/events.out.tfevents.1684134713.3144edec4884.864.0 +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 +66 -0
- unet/diffusion_pytorch_model.bin +3 -0
checkpoint-1000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7026349eaa5030e8c439ae73021a9a6e9844b7b51321046b052b4c6809941863
|
3 |
+
size 2421618099
|
checkpoint-1000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55315fb2f42187c5c72301260783c74cfcf8867171861d11b189c070bcdb136c
|
3 |
+
size 15755
|
checkpoint-1000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68cff80b680ddf6e7abbef98b5f336b97f9b5963e2209307f639383870e8cc71
|
3 |
+
size 557
|
checkpoint-1000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:223436be2788dc84d53d2c2e4303ade14df55ba01000214c925cafe35a59ad75
|
3 |
+
size 563
|
checkpoint-1000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1",
|
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": "gelu",
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 23,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.29.1",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
checkpoint-1000/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d6764e8719cddfec1de17ed6fbfa9dd0191dfd760d64ffa94991a1731b7f547
|
3 |
+
size 1361679905
|
checkpoint-1000/unet/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": [
|
9 |
+
5,
|
10 |
+
10,
|
11 |
+
20,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 1024,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"DownBlock2D"
|
32 |
+
],
|
33 |
+
"downsample_padding": 1,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"layers_per_block": 2,
|
40 |
+
"mid_block_only_cross_attention": null,
|
41 |
+
"mid_block_scale_factor": 1,
|
42 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
43 |
+
"norm_eps": 1e-05,
|
44 |
+
"norm_num_groups": 32,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"sample_size": 96,
|
53 |
+
"time_cond_proj_dim": null,
|
54 |
+
"time_embedding_act_fn": null,
|
55 |
+
"time_embedding_dim": null,
|
56 |
+
"time_embedding_type": "positional",
|
57 |
+
"timestep_post_act": null,
|
58 |
+
"up_block_types": [
|
59 |
+
"UpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D"
|
63 |
+
],
|
64 |
+
"upcast_attention": true,
|
65 |
+
"use_linear_projection": true
|
66 |
+
}
|
checkpoint-1000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4c0bb632bac3f89f6c4ce23151459707256468e445271b66d2e12331b4dc332
|
3 |
+
size 3463934693
|
checkpoint-2000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c1efbbb7b345ae12bc2a2fbd6b3ed98f452f5dda36b7f66b2439fab38d5a4a1
|
3 |
+
size 2421618099
|
checkpoint-2000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0be23eaf0e5c75669d6d8a83fcd7ccd3a100b412e14640189a443cd54fd7bae
|
3 |
+
size 15755
|
checkpoint-2000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd2de9749828adacdf103bf6e9592702bb7067a2c1df27dd62ab38c1eb8c070f
|
3 |
+
size 557
|
checkpoint-2000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb4f0b1924463e34e3dc4a27e2ebe7ee7a43bc8be36d5cff2a75500ff628d083
|
3 |
+
size 563
|
checkpoint-2000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1",
|
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": "gelu",
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 23,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.29.1",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
checkpoint-2000/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07687ee3eb68e4822e273e808f43c5cff5e1aeb12de1b5b16d12c65df5485adc
|
3 |
+
size 1361679905
|
checkpoint-2000/unet/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": [
|
9 |
+
5,
|
10 |
+
10,
|
11 |
+
20,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 1024,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"DownBlock2D"
|
32 |
+
],
|
33 |
+
"downsample_padding": 1,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"layers_per_block": 2,
|
40 |
+
"mid_block_only_cross_attention": null,
|
41 |
+
"mid_block_scale_factor": 1,
|
42 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
43 |
+
"norm_eps": 1e-05,
|
44 |
+
"norm_num_groups": 32,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"sample_size": 96,
|
53 |
+
"time_cond_proj_dim": null,
|
54 |
+
"time_embedding_act_fn": null,
|
55 |
+
"time_embedding_dim": null,
|
56 |
+
"time_embedding_type": "positional",
|
57 |
+
"timestep_post_act": null,
|
58 |
+
"up_block_types": [
|
59 |
+
"UpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D"
|
63 |
+
],
|
64 |
+
"upcast_attention": true,
|
65 |
+
"use_linear_projection": true
|
66 |
+
}
|
checkpoint-2000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4074cf72396515f93ebc2bc3fbd5e24f6d164000dd238a9470bb85f49780e2a8
|
3 |
+
size 3463934693
|
checkpoint-3000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:690592047601a89e215fff87ef7b7c0fc332f1f332dc2169666f4c73923982c3
|
3 |
+
size 2421618099
|
checkpoint-3000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72648b31fe6d6972ce090659be1ac2972fab2fd38022e6a2ddcc3ce61e6e5dd0
|
3 |
+
size 15755
|
checkpoint-3000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7daa6d278a3da98cc62309304bb5f21a5afd1b4ecfb927f2d2da2312a6b0b128
|
3 |
+
size 557
|
checkpoint-3000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4114290142c676ae450870c5c3dfafadcae7528c01110ca590c349c5816abf66
|
3 |
+
size 563
|
checkpoint-3000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1",
|
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": "gelu",
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 23,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.29.1",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
checkpoint-3000/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d082115e9e0ee0d7d531ab34fbdfa1f4a9cfc4c390877c9ace0c594c399e32f3
|
3 |
+
size 1361679905
|
checkpoint-3000/unet/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": [
|
9 |
+
5,
|
10 |
+
10,
|
11 |
+
20,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 1024,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"DownBlock2D"
|
32 |
+
],
|
33 |
+
"downsample_padding": 1,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"layers_per_block": 2,
|
40 |
+
"mid_block_only_cross_attention": null,
|
41 |
+
"mid_block_scale_factor": 1,
|
42 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
43 |
+
"norm_eps": 1e-05,
|
44 |
+
"norm_num_groups": 32,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"sample_size": 96,
|
53 |
+
"time_cond_proj_dim": null,
|
54 |
+
"time_embedding_act_fn": null,
|
55 |
+
"time_embedding_dim": null,
|
56 |
+
"time_embedding_type": "positional",
|
57 |
+
"timestep_post_act": null,
|
58 |
+
"up_block_types": [
|
59 |
+
"UpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D"
|
63 |
+
],
|
64 |
+
"upcast_attention": true,
|
65 |
+
"use_linear_projection": true
|
66 |
+
}
|
checkpoint-3000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0be43db6d1a7e486456de62a40bd7ecb52c401ba39f5f3d94f14d4dea9d73f52
|
3 |
+
size 3463934693
|
feature_extractor/preprocessor_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 224,
|
4 |
+
"width": 224
|
5 |
+
},
|
6 |
+
"do_center_crop": true,
|
7 |
+
"do_convert_rgb": true,
|
8 |
+
"do_normalize": true,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"feature_extractor_type": "CLIPFeatureExtractor",
|
12 |
+
"image_mean": [
|
13 |
+
0.48145466,
|
14 |
+
0.4578275,
|
15 |
+
0.40821073
|
16 |
+
],
|
17 |
+
"image_processor_type": "CLIPFeatureExtractor",
|
18 |
+
"image_std": [
|
19 |
+
0.26862954,
|
20 |
+
0.26130258,
|
21 |
+
0.27577711
|
22 |
+
],
|
23 |
+
"resample": 3,
|
24 |
+
"rescale_factor": 0.00392156862745098,
|
25 |
+
"size": {
|
26 |
+
"shortest_edge": 224
|
27 |
+
}
|
28 |
+
}
|
logs/dreambooth/1684134445.407711/events.out.tfevents.1684134445.3144edec4884.691.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daf7921f573d051e01b976c0cc21ef27762d8ee8ef4e3f0ebbe8589e4bdddf77
|
3 |
+
size 2687
|
logs/dreambooth/1684134445.4103186/hparams.yml
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
adam_beta1: 0.9
|
2 |
+
adam_beta2: 0.999
|
3 |
+
adam_epsilon: 1.0e-08
|
4 |
+
adam_weight_decay: 0.01
|
5 |
+
allow_tf32: false
|
6 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 1000
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
class_data_dir: =./dataset/office_building_sampled
|
10 |
+
class_prompt: architecture rendering of a office building.
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
enable_xformers_memory_efficient_attention: false
|
13 |
+
gradient_accumulation_steps: 1
|
14 |
+
gradient_checkpointing: true
|
15 |
+
hub_model_id: null
|
16 |
+
hub_token: null
|
17 |
+
instance_data_dir: ./dataset/office_building_pngProcessed
|
18 |
+
instance_prompt: architecture rendering of a t-arch office building.
|
19 |
+
learning_rate: 1.0e-06
|
20 |
+
local_rank: 0
|
21 |
+
logging_dir: logs
|
22 |
+
lr_num_cycles: 1
|
23 |
+
lr_power: 1.0
|
24 |
+
lr_scheduler: constant
|
25 |
+
lr_warmup_steps: 0
|
26 |
+
max_grad_norm: 1.0
|
27 |
+
max_train_steps: 3001
|
28 |
+
mixed_precision: null
|
29 |
+
num_class_images: 100
|
30 |
+
num_train_epochs: 201
|
31 |
+
num_validation_images: 4
|
32 |
+
offset_noise: false
|
33 |
+
output_dir: ./models/office-dbModel-v0-3
|
34 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
|
35 |
+
prior_generation_precision: null
|
36 |
+
prior_loss_weight: 1.0
|
37 |
+
push_to_hub: false
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 768
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
sample_batch_size: 4
|
43 |
+
scale_lr: false
|
44 |
+
seed: null
|
45 |
+
set_grads_to_none: false
|
46 |
+
tokenizer_name: null
|
47 |
+
train_batch_size: 1
|
48 |
+
train_text_encoder: true
|
49 |
+
use_8bit_adam: false
|
50 |
+
validation_prompt: null
|
51 |
+
validation_steps: 100
|
52 |
+
with_prior_preservation: false
|
logs/dreambooth/1684134521.9282608/events.out.tfevents.1684134521.3144edec4884.742.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cc5bb0f505dc74a03700421e00a81f52ee2a176e9a0c3c6903de9dd8fce5e53
|
3 |
+
size 2687
|
logs/dreambooth/1684134521.9308062/hparams.yml
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
adam_beta1: 0.9
|
2 |
+
adam_beta2: 0.999
|
3 |
+
adam_epsilon: 1.0e-08
|
4 |
+
adam_weight_decay: 0.01
|
5 |
+
allow_tf32: false
|
6 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 1000
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
class_data_dir: =./dataset/office_building_sampled
|
10 |
+
class_prompt: architecture rendering of a office building.
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
enable_xformers_memory_efficient_attention: false
|
13 |
+
gradient_accumulation_steps: 1
|
14 |
+
gradient_checkpointing: true
|
15 |
+
hub_model_id: null
|
16 |
+
hub_token: null
|
17 |
+
instance_data_dir: ./dataset/office_building_pngProcessed
|
18 |
+
instance_prompt: architecture rendering of a t-arch office building.
|
19 |
+
learning_rate: 1.0e-06
|
20 |
+
local_rank: 0
|
21 |
+
logging_dir: logs
|
22 |
+
lr_num_cycles: 1
|
23 |
+
lr_power: 1.0
|
24 |
+
lr_scheduler: constant
|
25 |
+
lr_warmup_steps: 0
|
26 |
+
max_grad_norm: 1.0
|
27 |
+
max_train_steps: 3001
|
28 |
+
mixed_precision: null
|
29 |
+
num_class_images: 100
|
30 |
+
num_train_epochs: 201
|
31 |
+
num_validation_images: 4
|
32 |
+
offset_noise: false
|
33 |
+
output_dir: ./models/office-dbModel-v0-3
|
34 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
|
35 |
+
prior_generation_precision: null
|
36 |
+
prior_loss_weight: 1.0
|
37 |
+
push_to_hub: false
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 768
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
sample_batch_size: 4
|
43 |
+
scale_lr: false
|
44 |
+
seed: null
|
45 |
+
set_grads_to_none: false
|
46 |
+
tokenizer_name: null
|
47 |
+
train_batch_size: 1
|
48 |
+
train_text_encoder: true
|
49 |
+
use_8bit_adam: false
|
50 |
+
validation_prompt: null
|
51 |
+
validation_steps: 100
|
52 |
+
with_prior_preservation: false
|
logs/dreambooth/1684134566.1052556/events.out.tfevents.1684134566.3144edec4884.780.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34ffba3eb10c3c6a5a278a90180410671923b793a62b726559d84d7607d63152
|
3 |
+
size 2687
|
logs/dreambooth/1684134566.1079392/hparams.yml
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
adam_beta1: 0.9
|
2 |
+
adam_beta2: 0.999
|
3 |
+
adam_epsilon: 1.0e-08
|
4 |
+
adam_weight_decay: 0.01
|
5 |
+
allow_tf32: false
|
6 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 1000
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
class_data_dir: =./dataset/office_building_sampled
|
10 |
+
class_prompt: architecture rendering of a office building.
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
enable_xformers_memory_efficient_attention: false
|
13 |
+
gradient_accumulation_steps: 1
|
14 |
+
gradient_checkpointing: true
|
15 |
+
hub_model_id: null
|
16 |
+
hub_token: null
|
17 |
+
instance_data_dir: ./dataset/office_building_pngProcessed
|
18 |
+
instance_prompt: architecture rendering of a t-arch office building.
|
19 |
+
learning_rate: 1.0e-06
|
20 |
+
local_rank: 0
|
21 |
+
logging_dir: logs
|
22 |
+
lr_num_cycles: 1
|
23 |
+
lr_power: 1.0
|
24 |
+
lr_scheduler: constant
|
25 |
+
lr_warmup_steps: 0
|
26 |
+
max_grad_norm: 1.0
|
27 |
+
max_train_steps: 3001
|
28 |
+
mixed_precision: null
|
29 |
+
num_class_images: 100
|
30 |
+
num_train_epochs: 201
|
31 |
+
num_validation_images: 4
|
32 |
+
offset_noise: false
|
33 |
+
output_dir: ./models/office-dbModel-v0-3
|
34 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
|
35 |
+
prior_generation_precision: null
|
36 |
+
prior_loss_weight: 1.0
|
37 |
+
push_to_hub: false
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 768
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
sample_batch_size: 4
|
43 |
+
scale_lr: false
|
44 |
+
seed: null
|
45 |
+
set_grads_to_none: false
|
46 |
+
tokenizer_name: null
|
47 |
+
train_batch_size: 1
|
48 |
+
train_text_encoder: true
|
49 |
+
use_8bit_adam: false
|
50 |
+
validation_prompt: null
|
51 |
+
validation_steps: 100
|
52 |
+
with_prior_preservation: false
|
logs/dreambooth/1684134653.766244/events.out.tfevents.1684134653.3144edec4884.823.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cf4f3731477487a6cbd5cbef029730987723beac87d78813a593fef1497aa2f
|
3 |
+
size 2611
|
logs/dreambooth/1684134653.7687936/hparams.yml
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
adam_beta1: 0.9
|
2 |
+
adam_beta2: 0.999
|
3 |
+
adam_epsilon: 1.0e-08
|
4 |
+
adam_weight_decay: 0.01
|
5 |
+
allow_tf32: false
|
6 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 1000
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
class_data_dir: null
|
10 |
+
class_prompt: architecture rendering of a office building.
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
enable_xformers_memory_efficient_attention: false
|
13 |
+
gradient_accumulation_steps: 1
|
14 |
+
gradient_checkpointing: true
|
15 |
+
hub_model_id: null
|
16 |
+
hub_token: null
|
17 |
+
instance_data_dir: ./dataset/office_building_pngProcessed
|
18 |
+
instance_prompt: architecture rendering of a t-arch office building.
|
19 |
+
learning_rate: 1.0e-06
|
20 |
+
local_rank: 0
|
21 |
+
logging_dir: logs
|
22 |
+
lr_num_cycles: 1
|
23 |
+
lr_power: 1.0
|
24 |
+
lr_scheduler: constant
|
25 |
+
lr_warmup_steps: 0
|
26 |
+
max_grad_norm: 1.0
|
27 |
+
max_train_steps: 3001
|
28 |
+
mixed_precision: null
|
29 |
+
num_class_images: 100
|
30 |
+
num_train_epochs: 201
|
31 |
+
num_validation_images: 4
|
32 |
+
offset_noise: false
|
33 |
+
output_dir: ./models/office-dbModel-v0-3
|
34 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
|
35 |
+
prior_generation_precision: null
|
36 |
+
prior_loss_weight: 1.0
|
37 |
+
push_to_hub: false
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 768
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
sample_batch_size: 4
|
43 |
+
scale_lr: false
|
44 |
+
seed: null
|
45 |
+
set_grads_to_none: false
|
46 |
+
tokenizer_name: null
|
47 |
+
train_batch_size: 1
|
48 |
+
train_text_encoder: true
|
49 |
+
use_8bit_adam: false
|
50 |
+
validation_prompt: null
|
51 |
+
validation_steps: 100
|
52 |
+
with_prior_preservation: false
|
logs/dreambooth/1684134713.7159472/events.out.tfevents.1684134713.3144edec4884.864.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20793f88de110f54e6d013512ed18b45f1bfa50fa41ef786f5d8647fbf16a1bb
|
3 |
+
size 2611
|
logs/dreambooth/1684134713.7184079/hparams.yml
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
adam_beta1: 0.9
|
2 |
+
adam_beta2: 0.999
|
3 |
+
adam_epsilon: 1.0e-08
|
4 |
+
adam_weight_decay: 0.01
|
5 |
+
allow_tf32: false
|
6 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 1000
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
class_data_dir: null
|
10 |
+
class_prompt: architecture rendering of a office building.
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
enable_xformers_memory_efficient_attention: false
|
13 |
+
gradient_accumulation_steps: 1
|
14 |
+
gradient_checkpointing: true
|
15 |
+
hub_model_id: null
|
16 |
+
hub_token: null
|
17 |
+
instance_data_dir: ./dataset/office_building_pngProcessed
|
18 |
+
instance_prompt: architecture rendering of a t-arch office building.
|
19 |
+
learning_rate: 1.0e-06
|
20 |
+
local_rank: 0
|
21 |
+
logging_dir: logs
|
22 |
+
lr_num_cycles: 1
|
23 |
+
lr_power: 1.0
|
24 |
+
lr_scheduler: constant
|
25 |
+
lr_warmup_steps: 0
|
26 |
+
max_grad_norm: 1.0
|
27 |
+
max_train_steps: 3001
|
28 |
+
mixed_precision: null
|
29 |
+
num_class_images: 100
|
30 |
+
num_train_epochs: 201
|
31 |
+
num_validation_images: 4
|
32 |
+
offset_noise: false
|
33 |
+
output_dir: ./models/office-dbModel-v0-3
|
34 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
|
35 |
+
prior_generation_precision: null
|
36 |
+
prior_loss_weight: 1.0
|
37 |
+
push_to_hub: false
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 768
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
sample_batch_size: 4
|
43 |
+
scale_lr: false
|
44 |
+
seed: null
|
45 |
+
set_grads_to_none: false
|
46 |
+
tokenizer_name: null
|
47 |
+
train_batch_size: 1
|
48 |
+
train_text_encoder: true
|
49 |
+
use_8bit_adam: true
|
50 |
+
validation_prompt: null
|
51 |
+
validation_steps: 100
|
52 |
+
with_prior_preservation: false
|
logs/dreambooth/events.out.tfevents.1684134445.3144edec4884.691.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3e5ed27fbed3b242e19f090e082fbaa5bfa5ad88308e19e562ee75815ce62ae
|
3 |
+
size 88
|
logs/dreambooth/events.out.tfevents.1684134521.3144edec4884.742.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f4bc1bb8df308814ae865a2d75ec2c39fea5fcb9243a23b82cc68c98f3ad4f5
|
3 |
+
size 88
|
logs/dreambooth/events.out.tfevents.1684134566.3144edec4884.780.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b294985b58b1624e813beff7cdc55ef271cba77dcc0dcb259619c4f620617f91
|
3 |
+
size 88
|
logs/dreambooth/events.out.tfevents.1684134653.3144edec4884.823.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baf1f6e4da29bb0434ee4b0f782c861c1892b3bf9e732d559183383c58b32941
|
3 |
+
size 88
|
logs/dreambooth/events.out.tfevents.1684134713.3144edec4884.864.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6433fe5bd4412c4cdfd12a46fcdf7a2bd088e82f403bb745331c84f32633bfd0
|
3 |
+
size 251918
|
model_index.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
"transformers",
|
6 |
+
"CLIPFeatureExtractor"
|
7 |
+
],
|
8 |
+
"requires_safety_checker": false,
|
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": "0.17.0.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": "v_prediction",
|
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": "stabilityai/stable-diffusion-2-1",
|
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": "gelu",
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 23,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.29.1",
|
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:f0ca08d7008f4ba719e15f1925d61be1ec4b117e09089d56fdf54028a65ff2c1
|
3 |
+
size 1361679905
|
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": "!",
|
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 |
+
"clean_up_tokenization_spaces": true,
|
12 |
+
"do_lower_case": true,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<|endoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"errors": "replace",
|
22 |
+
"model_max_length": 77,
|
23 |
+
"pad_token": "<|endoftext|>",
|
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 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": [
|
9 |
+
5,
|
10 |
+
10,
|
11 |
+
20,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 1024,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"DownBlock2D"
|
32 |
+
],
|
33 |
+
"downsample_padding": 1,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"layers_per_block": 2,
|
40 |
+
"mid_block_only_cross_attention": null,
|
41 |
+
"mid_block_scale_factor": 1,
|
42 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
43 |
+
"norm_eps": 1e-05,
|
44 |
+
"norm_num_groups": 32,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"sample_size": 96,
|
53 |
+
"time_cond_proj_dim": null,
|
54 |
+
"time_embedding_act_fn": null,
|
55 |
+
"time_embedding_dim": null,
|
56 |
+
"time_embedding_type": "positional",
|
57 |
+
"timestep_post_act": null,
|
58 |
+
"up_block_types": [
|
59 |
+
"UpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D"
|
63 |
+
],
|
64 |
+
"upcast_attention": true,
|
65 |
+
"use_linear_projection": true
|
66 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73d3f8200610b5d924447fc7ab61777d604feb0fbe63ae670f00eb9d162994b8
|
3 |
+
size 3463934693
|