End of training
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +43 -0
- checkpoint-10000/optimizer.bin +3 -0
- checkpoint-10000/random_states_0.pkl +3 -0
- checkpoint-10000/scheduler.bin +3 -0
- checkpoint-10000/text_encoder/config.json +25 -0
- checkpoint-10000/text_encoder/model.safetensors +3 -0
- checkpoint-10000/unet/config.json +68 -0
- checkpoint-10000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-20000/optimizer.bin +3 -0
- checkpoint-20000/random_states_0.pkl +3 -0
- checkpoint-20000/scheduler.bin +3 -0
- checkpoint-20000/text_encoder/config.json +25 -0
- checkpoint-20000/text_encoder/model.safetensors +3 -0
- checkpoint-20000/unet/config.json +68 -0
- checkpoint-20000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-30000/optimizer.bin +3 -0
- checkpoint-30000/random_states_0.pkl +3 -0
- checkpoint-30000/scheduler.bin +3 -0
- checkpoint-30000/text_encoder/config.json +25 -0
- checkpoint-30000/text_encoder/model.safetensors +3 -0
- checkpoint-30000/unet/config.json +68 -0
- checkpoint-30000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-40000/optimizer.bin +3 -0
- checkpoint-40000/random_states_0.pkl +3 -0
- checkpoint-40000/scheduler.bin +3 -0
- checkpoint-40000/text_encoder/config.json +25 -0
- checkpoint-40000/text_encoder/model.safetensors +3 -0
- checkpoint-40000/unet/config.json +68 -0
- checkpoint-40000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-50000/optimizer.bin +3 -0
- checkpoint-50000/random_states_0.pkl +3 -0
- checkpoint-50000/scheduler.bin +3 -0
- checkpoint-50000/text_encoder/config.json +25 -0
- checkpoint-50000/text_encoder/model.safetensors +3 -0
- checkpoint-50000/unet/config.json +68 -0
- checkpoint-50000/unet/diffusion_pytorch_model.safetensors +3 -0
- feature_extractor/preprocessor_config.json +27 -0
- logs/dreambooth/1731230427.773032/events.out.tfevents.1731230427.cec3fe7046df.4607.1 +3 -0
- logs/dreambooth/1731230427.774833/hparams.yml +60 -0
- logs/dreambooth/events.out.tfevents.1731230427.cec3fe7046df.4607.0 +3 -0
- model_index.json +38 -0
- safety_checker/config.json +28 -0
- safety_checker/model.safetensors +3 -0
- scheduler/scheduler_config.json +15 -0
- text_encoder/config.json +25 -0
- text_encoder/model.safetensors +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +30 -0
- tokenizer/tokenizer_config.json +32 -0
- tokenizer/vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: KHongJae/full_train_TE_D_0_10000to50000
|
3 |
+
library_name: diffusers
|
4 |
+
license: creativeml-openrail-m
|
5 |
+
tags:
|
6 |
+
- text-to-image
|
7 |
+
- dreambooth
|
8 |
+
- diffusers-training
|
9 |
+
- stable-diffusion
|
10 |
+
- stable-diffusion-diffusers
|
11 |
+
inference: true
|
12 |
+
instance_prompt: 배불러
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
|
19 |
+
# DreamBooth - KHongJae/full_train_TE_D_0_50000to100000
|
20 |
+
|
21 |
+
This is a dreambooth model derived from KHongJae/full_train_TE_D_0_10000to50000. The weights were trained on 배불러 using [DreamBooth](https://dreambooth.github.io/).
|
22 |
+
You can find some example images in the following.
|
23 |
+
|
24 |
+
|
25 |
+
|
26 |
+
DreamBooth for the text encoder was enabled: True.
|
27 |
+
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
#### How to use
|
32 |
+
|
33 |
+
```python
|
34 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
35 |
+
```
|
36 |
+
|
37 |
+
#### Limitations and bias
|
38 |
+
|
39 |
+
[TODO: provide examples of latent issues and potential remediations]
|
40 |
+
|
41 |
+
## Training details
|
42 |
+
|
43 |
+
[TODO: describe the data used to train the model]
|
checkpoint-10000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b33943b0c750f2223f0060f773b85da1ec589d801cfaae75a7da0639a362677e
|
3 |
+
size 7861403640
|
checkpoint-10000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91836c2953916229cd6ca42aaea4af7a8ceee750eb9614232110fe55d915393c
|
3 |
+
size 14408
|
checkpoint-10000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06effd520766ea4bf433e328069a8f372a51c114ac80e230f0948163719cd0c3
|
3 |
+
size 1000
|
checkpoint-10000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "KHongJae/full_train_TE_D_0_10000to50000",
|
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": "float32",
|
23 |
+
"transformers_version": "4.44.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
checkpoint-10000/text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02902191e574ab29212f423519fabd37499e8cf375e690e134da6281738e199d
|
3 |
+
size 492265168
|
checkpoint-10000/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "KHongJae/full_train_TE_D_0_10000to50000",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": null,
|
9 |
+
"attention_head_dim": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
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 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-10000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abe7734b809844e9f10c73fc177901e874d13c3dc565297f427145cb090f2491
|
3 |
+
size 3438167536
|
checkpoint-20000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd9f0fee9f91eeac10519b5dac8e9acb17f9d1546b3259fc4d7a3c7808bfcd1f
|
3 |
+
size 7861403640
|
checkpoint-20000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f8ed448dacbf7be76f443c3a19c798acda42d9800385bfe3c4b84179aedfd33
|
3 |
+
size 14408
|
checkpoint-20000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0cff3bf009736764481832c96422557370f2c9640bf88f5ac5a133764d6a4ba
|
3 |
+
size 1000
|
checkpoint-20000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "KHongJae/full_train_TE_D_0_10000to50000",
|
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": "float32",
|
23 |
+
"transformers_version": "4.44.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
checkpoint-20000/text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:544f356a1f8adcda06b2af932bd043c4013c5c8c59f23cc47b38556f1cb806bc
|
3 |
+
size 492265168
|
checkpoint-20000/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "KHongJae/full_train_TE_D_0_10000to50000",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": null,
|
9 |
+
"attention_head_dim": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
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 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-20000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84440f1dafe020f7b48fa27dd56e16389539690f9e128c69d9ecc70c3d3e5d3e
|
3 |
+
size 3438167536
|
checkpoint-30000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28037559b61243cb216bcb23e587d37cf1dba0113db6c4afa648322c923de09d
|
3 |
+
size 7861403640
|
checkpoint-30000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd9ae41f51fa98845e069e593da262ec9b8eab4c10a90b2ad8ab9dbb17ba41d7
|
3 |
+
size 14408
|
checkpoint-30000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d2faaf212aa126fcd796f16fbf64e7b7d1c2ed68667cd1f56cf1968fa847cc3
|
3 |
+
size 1000
|
checkpoint-30000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "KHongJae/full_train_TE_D_0_10000to50000",
|
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": "float32",
|
23 |
+
"transformers_version": "4.44.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
checkpoint-30000/text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:902572963a560f5c658a35051775c3dd260962c608dfa5e66678a5775b4d84ad
|
3 |
+
size 492265168
|
checkpoint-30000/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "KHongJae/full_train_TE_D_0_10000to50000",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": null,
|
9 |
+
"attention_head_dim": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
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 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-30000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57b1e7cbff75768a3afbcca8f90747ddd3a69b504e2271cab7fa654963ab7035
|
3 |
+
size 3438167536
|
checkpoint-40000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cce62e622c8576d9a120333df22b20d57e3efbed6d608b64ddbe18ccb98c513e
|
3 |
+
size 7861403640
|
checkpoint-40000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2320c239ed47d4db0efdf9d69427f17eca835ea4e2fcc241a9eb22380f610783
|
3 |
+
size 14408
|
checkpoint-40000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75f2643b5c13a9dffe551c00261dd7710fb82717e4dee239483895407e584871
|
3 |
+
size 1000
|
checkpoint-40000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "KHongJae/full_train_TE_D_0_10000to50000",
|
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": "float32",
|
23 |
+
"transformers_version": "4.44.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
checkpoint-40000/text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67dd8e3136a66bb8533bf7234e2b1e4e1a3d11b99008c44aa67e2e7591d39522
|
3 |
+
size 492265168
|
checkpoint-40000/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "KHongJae/full_train_TE_D_0_10000to50000",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": null,
|
9 |
+
"attention_head_dim": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
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 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-40000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ed2a7468975dfdcaed2d4f09b912ed1a7a1ed13533458b6d70079876cec4e90
|
3 |
+
size 3438167536
|
checkpoint-50000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5c1bae2c2e4ec0b1c52a4a5ad3b91b0cc8015d58d18e46393d2e159092cb8f5
|
3 |
+
size 7861403640
|
checkpoint-50000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae1415547306a49ce29343fc9de921ba8ae84bab8196be8618e7cbb57c81d6c6
|
3 |
+
size 14408
|
checkpoint-50000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c1820c269851ea47fb72d88fc84394be79b5650cea5639cd71201cab443d3bf
|
3 |
+
size 1000
|
checkpoint-50000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "KHongJae/full_train_TE_D_0_10000to50000",
|
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": "float32",
|
23 |
+
"transformers_version": "4.44.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
checkpoint-50000/text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d668dcc73d942ca035f51705ea782e33e657281678a8c25feda80fc1e76074ba
|
3 |
+
size 492265168
|
checkpoint-50000/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "KHongJae/full_train_TE_D_0_10000to50000",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": null,
|
9 |
+
"attention_head_dim": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
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 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-50000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0197c908141cda708ec2338e2281c18933e09fb9f6cc3cc5638bd081a80cabb
|
3 |
+
size 3438167536
|
feature_extractor/preprocessor_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"image_mean": [
|
12 |
+
0.48145466,
|
13 |
+
0.4578275,
|
14 |
+
0.40821073
|
15 |
+
],
|
16 |
+
"image_processor_type": "CLIPFeatureExtractor",
|
17 |
+
"image_std": [
|
18 |
+
0.26862954,
|
19 |
+
0.26130258,
|
20 |
+
0.27577711
|
21 |
+
],
|
22 |
+
"resample": 3,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"shortest_edge": 224
|
26 |
+
}
|
27 |
+
}
|
logs/dreambooth/1731230427.773032/events.out.tfevents.1731230427.cec3fe7046df.4607.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acced94dafb9705dadab396f7466d9b5cf81b85a395a85eb61e352f50f509601
|
3 |
+
size 2790
|
logs/dreambooth/1731230427.774833/hparams.yml
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 10000
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
class_data_dir: null
|
10 |
+
class_labels_conditioning: null
|
11 |
+
class_prompt: null
|
12 |
+
dataloader_num_workers: 0
|
13 |
+
enable_xformers_memory_efficient_attention: false
|
14 |
+
gradient_accumulation_steps: 1
|
15 |
+
gradient_checkpointing: false
|
16 |
+
hub_model_id: null
|
17 |
+
hub_token: null
|
18 |
+
instance_data_dir: /content/full_caption_rmtxt
|
19 |
+
instance_prompt: "\uBC30\uBD88\uB7EC"
|
20 |
+
learning_rate: 1.0e-06
|
21 |
+
local_rank: -1
|
22 |
+
logging_dir: logs
|
23 |
+
lr_num_cycles: 1
|
24 |
+
lr_power: 1.0
|
25 |
+
lr_scheduler: constant
|
26 |
+
lr_warmup_steps: 0
|
27 |
+
max_grad_norm: 1.0
|
28 |
+
max_train_steps: 50000
|
29 |
+
mixed_precision: null
|
30 |
+
num_class_images: 100
|
31 |
+
num_train_epochs: 2
|
32 |
+
num_validation_images: 4
|
33 |
+
offset_noise: false
|
34 |
+
output_dir: full_train_TE_D_0_50000to100000
|
35 |
+
pre_compute_text_embeddings: false
|
36 |
+
pretrained_model_name_or_path: KHongJae/full_train_TE_D_0_10000to50000
|
37 |
+
prior_generation_precision: null
|
38 |
+
prior_loss_weight: 1.0
|
39 |
+
push_to_hub: true
|
40 |
+
report_to: tensorboard
|
41 |
+
resolution: 768
|
42 |
+
resume_from_checkpoint: null
|
43 |
+
revision: null
|
44 |
+
sample_batch_size: 4
|
45 |
+
scale_lr: false
|
46 |
+
seed: null
|
47 |
+
set_grads_to_none: false
|
48 |
+
skip_save_text_encoder: false
|
49 |
+
snr_gamma: null
|
50 |
+
text_encoder_use_attention_mask: false
|
51 |
+
tokenizer_max_length: null
|
52 |
+
tokenizer_name: null
|
53 |
+
train_batch_size: 1
|
54 |
+
train_text_encoder: true
|
55 |
+
use_8bit_adam: false
|
56 |
+
validation_prompt: null
|
57 |
+
validation_scheduler: DPMSolverMultistepScheduler
|
58 |
+
validation_steps: 100
|
59 |
+
variant: null
|
60 |
+
with_prior_preservation: false
|
logs/dreambooth/events.out.tfevents.1731230427.cec3fe7046df.4607.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77e0dcbf8eca07ec5ce9badc7161a6bab1687f010bb1dbfafda4e0abfdf43ff3
|
3 |
+
size 4267068
|
model_index.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"_name_or_path": "KHongJae/full_train_TE_D_0_10000to50000",
|
5 |
+
"feature_extractor": [
|
6 |
+
"transformers",
|
7 |
+
"CLIPFeatureExtractor"
|
8 |
+
],
|
9 |
+
"image_encoder": [
|
10 |
+
null,
|
11 |
+
null
|
12 |
+
],
|
13 |
+
"requires_safety_checker": true,
|
14 |
+
"safety_checker": [
|
15 |
+
"stable_diffusion",
|
16 |
+
"StableDiffusionSafetyChecker"
|
17 |
+
],
|
18 |
+
"scheduler": [
|
19 |
+
"diffusers",
|
20 |
+
"PNDMScheduler"
|
21 |
+
],
|
22 |
+
"text_encoder": [
|
23 |
+
"transformers",
|
24 |
+
"CLIPTextModel"
|
25 |
+
],
|
26 |
+
"tokenizer": [
|
27 |
+
"transformers",
|
28 |
+
"CLIPTokenizer"
|
29 |
+
],
|
30 |
+
"unet": [
|
31 |
+
"diffusers",
|
32 |
+
"UNet2DConditionModel"
|
33 |
+
],
|
34 |
+
"vae": [
|
35 |
+
"diffusers",
|
36 |
+
"AutoencoderKL"
|
37 |
+
]
|
38 |
+
}
|
safety_checker/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/root/.cache/huggingface/hub/models--KHongJae--full_train_TE_D_0_10000to50000/snapshots/cf9fc93a6e77e435b562b602459c6bf53ec4020f/safety_checker",
|
3 |
+
"architectures": [
|
4 |
+
"StableDiffusionSafetyChecker"
|
5 |
+
],
|
6 |
+
"initializer_factor": 1.0,
|
7 |
+
"logit_scale_init_value": 2.6592,
|
8 |
+
"model_type": "clip",
|
9 |
+
"projection_dim": 768,
|
10 |
+
"text_config": {
|
11 |
+
"dropout": 0.0,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"model_type": "clip_text_model",
|
15 |
+
"num_attention_heads": 12
|
16 |
+
},
|
17 |
+
"torch_dtype": "float32",
|
18 |
+
"transformers_version": "4.44.2",
|
19 |
+
"vision_config": {
|
20 |
+
"dropout": 0.0,
|
21 |
+
"hidden_size": 1024,
|
22 |
+
"intermediate_size": 4096,
|
23 |
+
"model_type": "clip_vision_model",
|
24 |
+
"num_attention_heads": 16,
|
25 |
+
"num_hidden_layers": 24,
|
26 |
+
"patch_size": 14
|
27 |
+
}
|
28 |
+
}
|
safety_checker/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
|
3 |
+
size 1215979664
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.32.0.dev0",
|
4 |
+
"beta_end": 0.012,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.00085,
|
7 |
+
"clip_sample": false,
|
8 |
+
"num_train_timesteps": 1000,
|
9 |
+
"prediction_type": "epsilon",
|
10 |
+
"set_alpha_to_one": false,
|
11 |
+
"skip_prk_steps": true,
|
12 |
+
"steps_offset": 1,
|
13 |
+
"timestep_spacing": "leading",
|
14 |
+
"trained_betas": null
|
15 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "KHongJae/full_train_TE_D_0_10000to50000",
|
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": "float32",
|
23 |
+
"transformers_version": "4.44.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d668dcc73d942ca035f51705ea782e33e657281678a8c25feda80fc1e76074ba
|
3 |
+
size 492265168
|
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 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"49406": {
|
5 |
+
"content": "<|startoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"49407": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
}
|
20 |
+
},
|
21 |
+
"bos_token": "<|startoftext|>",
|
22 |
+
"clean_up_tokenization_spaces": true,
|
23 |
+
"do_lower_case": true,
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
+
"errors": "replace",
|
26 |
+
"model_max_length": 77,
|
27 |
+
"pad_token": "<|endoftext|>",
|
28 |
+
"processor_class": "CLIPProcessor",
|
29 |
+
"tokenizer_class": "CLIPTokenizer",
|
30 |
+
"trust_remote_code": false,
|
31 |
+
"unk_token": "<|endoftext|>"
|
32 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|