patrickvonplaten
commited on
Commit
·
82fcf70
1
Parent(s):
cdb3cf0
End of training
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +5 -4
- checkpoint-10/optimizer.bin +2 -2
- checkpoint-10/random_states_0.pkl +1 -1
- checkpoint-10/text_encoder/config.json +25 -0
- checkpoint-10/text_encoder/pytorch_model.bin +3 -0
- checkpoint-10/unet/config.json +56 -0
- checkpoint-10/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-100/optimizer.bin +2 -2
- checkpoint-100/random_states_0.pkl +1 -1
- checkpoint-100/text_encoder/config.json +25 -0
- checkpoint-100/text_encoder/pytorch_model.bin +3 -0
- checkpoint-100/unet/config.json +56 -0
- checkpoint-100/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-110/optimizer.bin +2 -2
- checkpoint-110/random_states_0.pkl +1 -1
- checkpoint-110/text_encoder/config.json +25 -0
- checkpoint-110/text_encoder/pytorch_model.bin +3 -0
- checkpoint-110/unet/config.json +56 -0
- checkpoint-110/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-120/optimizer.bin +2 -2
- checkpoint-120/random_states_0.pkl +1 -1
- checkpoint-120/text_encoder/config.json +25 -0
- checkpoint-120/text_encoder/pytorch_model.bin +3 -0
- checkpoint-120/unet/config.json +56 -0
- checkpoint-120/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-130/optimizer.bin +2 -2
- checkpoint-130/random_states_0.pkl +1 -1
- checkpoint-130/text_encoder/config.json +25 -0
- checkpoint-130/text_encoder/pytorch_model.bin +3 -0
- checkpoint-130/unet/config.json +56 -0
- checkpoint-130/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-140/optimizer.bin +2 -2
- checkpoint-140/random_states_0.pkl +1 -1
- checkpoint-140/text_encoder/config.json +25 -0
- checkpoint-140/text_encoder/pytorch_model.bin +3 -0
- checkpoint-140/unet/config.json +56 -0
- checkpoint-140/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-150/optimizer.bin +2 -2
- checkpoint-150/random_states_0.pkl +1 -1
- checkpoint-150/text_encoder/config.json +25 -0
- checkpoint-150/text_encoder/pytorch_model.bin +3 -0
- checkpoint-150/unet/config.json +56 -0
- checkpoint-150/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-20/optimizer.bin +2 -2
- checkpoint-20/random_states_0.pkl +1 -1
- checkpoint-20/text_encoder/config.json +25 -0
- checkpoint-20/text_encoder/pytorch_model.bin +3 -0
- checkpoint-20/unet/config.json +56 -0
- checkpoint-20/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-30/optimizer.bin +2 -2
README.md
CHANGED
@@ -8,14 +8,15 @@ tags:
|
|
8 |
- stable-diffusion-diffusers
|
9 |
- text-to-image
|
10 |
- diffusers
|
11 |
-
-
|
12 |
inference: true
|
13 |
---
|
14 |
|
15 |
-
#
|
16 |
|
17 |
-
|
|
|
18 |
|
19 |
|
20 |
|
21 |
-
|
|
|
8 |
- stable-diffusion-diffusers
|
9 |
- text-to-image
|
10 |
- diffusers
|
11 |
+
- dreambooth
|
12 |
inference: true
|
13 |
---
|
14 |
|
15 |
+
# DreamBooth - patrickvonplaten/dog-example-demo
|
16 |
|
17 |
+
This is a dreambooth model derived from hf-internal-testing/tiny-stable-diffusion-pipe. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/).
|
18 |
+
You can find some example images in the following.
|
19 |
|
20 |
|
21 |
|
22 |
+
DreamBooth for the text encoder was enabled: True.
|
checkpoint-10/optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3265a38655aace74f71dcdb0fe4ef529eda1d46c2105c1c811915d92ba4869c6
|
3 |
+
size 12286505
|
checkpoint-10/random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14663
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aa38463cae9b8eee66a145406766c594f816edd4066fa2a4f653a3b932f1ab3
|
3 |
size 14663
|
checkpoint-10/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hf-internal-testing/tiny-stable-diffusion-pipe",
|
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": 32,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 37,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 4,
|
19 |
+
"num_hidden_layers": 5,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.29.0.dev0",
|
24 |
+
"vocab_size": 1000
|
25 |
+
}
|
checkpoint-10/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:874811755cab3060494d8ab50e3a2d9599858daac6c290bd11662a39f8e9cb95
|
3 |
+
size 302896
|
checkpoint-10/unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"_name_or_path": "hf-internal-testing/tiny-stable-diffusion-pipe",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": 8,
|
9 |
+
"block_out_channels": [
|
10 |
+
32,
|
11 |
+
64
|
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": 32,
|
19 |
+
"cross_attention_norm": null,
|
20 |
+
"down_block_types": [
|
21 |
+
"DownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D"
|
23 |
+
],
|
24 |
+
"downsample_padding": 1,
|
25 |
+
"dropout": 0.0,
|
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": 32,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_act_fn": null,
|
47 |
+
"time_embedding_dim": null,
|
48 |
+
"time_embedding_type": "positional",
|
49 |
+
"timestep_post_act": null,
|
50 |
+
"up_block_types": [
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"UpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
checkpoint-10/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d51423dcb46dc2681e8cd56e7ed254b4dbbb25ba27a202c8aad465cf7b9afa9b
|
3 |
+
size 5834433
|
checkpoint-100/optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f3fae8e4facdf13442416909b6dd1d524c75898f47c5f2a75c0fbaa8fd5c679
|
3 |
+
size 12286505
|
checkpoint-100/random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14663
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e3a452c5c9410932fb5114d25ceb81dc6cddc49b3617140c7d9f39ea88c764f
|
3 |
size 14663
|
checkpoint-100/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hf-internal-testing/tiny-stable-diffusion-pipe",
|
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": 32,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 37,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 4,
|
19 |
+
"num_hidden_layers": 5,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.29.0.dev0",
|
24 |
+
"vocab_size": 1000
|
25 |
+
}
|
checkpoint-100/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f85fc8e27d3a23df1040a66d7fa57d011551a3e3008e3faeab3acd6ef6045357
|
3 |
+
size 302896
|
checkpoint-100/unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"_name_or_path": "hf-internal-testing/tiny-stable-diffusion-pipe",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": 8,
|
9 |
+
"block_out_channels": [
|
10 |
+
32,
|
11 |
+
64
|
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": 32,
|
19 |
+
"cross_attention_norm": null,
|
20 |
+
"down_block_types": [
|
21 |
+
"DownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D"
|
23 |
+
],
|
24 |
+
"downsample_padding": 1,
|
25 |
+
"dropout": 0.0,
|
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": 32,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_act_fn": null,
|
47 |
+
"time_embedding_dim": null,
|
48 |
+
"time_embedding_type": "positional",
|
49 |
+
"timestep_post_act": null,
|
50 |
+
"up_block_types": [
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"UpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
checkpoint-100/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89c59427674339534a4a5033ef0ef8360d4f3e75f881830b11db9384484919c9
|
3 |
+
size 5834433
|
checkpoint-110/optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52c686c32adb659b922d6c02d0ec3884f5ef8a5159014de9d76128a24cafddf8
|
3 |
+
size 12286505
|
checkpoint-110/random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14663
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5df58267041fdc11b9d535684fa89ff3a3b842903cc3af315e646adcf645950
|
3 |
size 14663
|
checkpoint-110/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dog-example-demo/checkpoint-100",
|
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": 32,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 37,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 4,
|
19 |
+
"num_hidden_layers": 5,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.29.0.dev0",
|
24 |
+
"vocab_size": 1000
|
25 |
+
}
|
checkpoint-110/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cd2911ef79dd8c6acb16ea8c726b0f52c0a84b9aec21e333e5c35bdc863076b
|
3 |
+
size 302896
|
checkpoint-110/unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"_name_or_path": "dog-example-demo/checkpoint-100",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": 8,
|
9 |
+
"block_out_channels": [
|
10 |
+
32,
|
11 |
+
64
|
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": 32,
|
19 |
+
"cross_attention_norm": null,
|
20 |
+
"down_block_types": [
|
21 |
+
"DownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D"
|
23 |
+
],
|
24 |
+
"downsample_padding": 1,
|
25 |
+
"dropout": 0.0,
|
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": 32,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_act_fn": null,
|
47 |
+
"time_embedding_dim": null,
|
48 |
+
"time_embedding_type": "positional",
|
49 |
+
"timestep_post_act": null,
|
50 |
+
"up_block_types": [
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"UpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
checkpoint-110/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4dc90a448942fcd511e9fe841b767349626e45f50c59cf1903037fbc6554e8d
|
3 |
+
size 5834433
|
checkpoint-120/optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4696def2a6ae294bb2056bfea394533764826f4169eeb048a7d7a1bddee13fd
|
3 |
+
size 12286505
|
checkpoint-120/random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14663
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d54cc37f72998cbfafdcb8ddf66684aee4fe98fbf4ae3f0198dc021018009a59
|
3 |
size 14663
|
checkpoint-120/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dog-example-demo/checkpoint-100",
|
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": 32,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 37,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 4,
|
19 |
+
"num_hidden_layers": 5,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.29.0.dev0",
|
24 |
+
"vocab_size": 1000
|
25 |
+
}
|
checkpoint-120/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bf4c826a159a2efe09bca89b688095cc293d07447e643b0d2f1d3f6b814ff63
|
3 |
+
size 302896
|
checkpoint-120/unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"_name_or_path": "dog-example-demo/checkpoint-100",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": 8,
|
9 |
+
"block_out_channels": [
|
10 |
+
32,
|
11 |
+
64
|
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": 32,
|
19 |
+
"cross_attention_norm": null,
|
20 |
+
"down_block_types": [
|
21 |
+
"DownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D"
|
23 |
+
],
|
24 |
+
"downsample_padding": 1,
|
25 |
+
"dropout": 0.0,
|
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": 32,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_act_fn": null,
|
47 |
+
"time_embedding_dim": null,
|
48 |
+
"time_embedding_type": "positional",
|
49 |
+
"timestep_post_act": null,
|
50 |
+
"up_block_types": [
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"UpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
checkpoint-120/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f49e0dfc7620af5a7373a873e7cfe530485543b65298d6422d779d79e69d906c
|
3 |
+
size 5834433
|
checkpoint-130/optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a93149f65972fd5b2f7f93a73962e0dd6c6189adca5a63ced41fe3757815d6c
|
3 |
+
size 12286505
|
checkpoint-130/random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14663
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae07e0e5563ecb5966297dc3ab71c3a6c8ed5039a87e51bd553c206f5e0c356e
|
3 |
size 14663
|
checkpoint-130/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dog-example-demo/checkpoint-100",
|
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": 32,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 37,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 4,
|
19 |
+
"num_hidden_layers": 5,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.29.0.dev0",
|
24 |
+
"vocab_size": 1000
|
25 |
+
}
|
checkpoint-130/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9ba95c28991ea32e2e2053ea6d4cc33db14eeefb6a00cffd4754680559bdf0e
|
3 |
+
size 302896
|
checkpoint-130/unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"_name_or_path": "dog-example-demo/checkpoint-100",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": 8,
|
9 |
+
"block_out_channels": [
|
10 |
+
32,
|
11 |
+
64
|
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": 32,
|
19 |
+
"cross_attention_norm": null,
|
20 |
+
"down_block_types": [
|
21 |
+
"DownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D"
|
23 |
+
],
|
24 |
+
"downsample_padding": 1,
|
25 |
+
"dropout": 0.0,
|
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": 32,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_act_fn": null,
|
47 |
+
"time_embedding_dim": null,
|
48 |
+
"time_embedding_type": "positional",
|
49 |
+
"timestep_post_act": null,
|
50 |
+
"up_block_types": [
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"UpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
checkpoint-130/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5fba5414ffa90b42a92e6d078e39a4f348d7876956ad332d147a626e680be71
|
3 |
+
size 5834433
|
checkpoint-140/optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db7dbb8f1bc543c132b62d90d8ef7411ef5630264f25aa84a2e6a054980dbf65
|
3 |
+
size 12286505
|
checkpoint-140/random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14663
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4e49ee9e5df2ea8aa7d2d87ab70e762ce669b2f268b71484fa2b36b564c3b01
|
3 |
size 14663
|
checkpoint-140/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dog-example-demo/checkpoint-100",
|
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": 32,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 37,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 4,
|
19 |
+
"num_hidden_layers": 5,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.29.0.dev0",
|
24 |
+
"vocab_size": 1000
|
25 |
+
}
|
checkpoint-140/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a74f0bd24e3c09f00ecca2cb1fa55638f89831df4fd67cd30fa594c230946adf
|
3 |
+
size 302896
|
checkpoint-140/unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"_name_or_path": "dog-example-demo/checkpoint-100",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": 8,
|
9 |
+
"block_out_channels": [
|
10 |
+
32,
|
11 |
+
64
|
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": 32,
|
19 |
+
"cross_attention_norm": null,
|
20 |
+
"down_block_types": [
|
21 |
+
"DownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D"
|
23 |
+
],
|
24 |
+
"downsample_padding": 1,
|
25 |
+
"dropout": 0.0,
|
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": 32,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_act_fn": null,
|
47 |
+
"time_embedding_dim": null,
|
48 |
+
"time_embedding_type": "positional",
|
49 |
+
"timestep_post_act": null,
|
50 |
+
"up_block_types": [
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"UpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
checkpoint-140/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:893656cd7468de382807b042ea6f4896e9cc7ba57a9762b0c151b627875a2051
|
3 |
+
size 5834433
|
checkpoint-150/optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c624dc681d35e85aa2cb1d419b8d3ad554affe55182793545c111b49e2003151
|
3 |
+
size 12286505
|
checkpoint-150/random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14663
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77175279e53b037037fc4a8a7b97bd3bee9e82f04ec4f340a09e948ae1a52474
|
3 |
size 14663
|
checkpoint-150/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dog-example-demo/checkpoint-100",
|
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": 32,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 37,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 4,
|
19 |
+
"num_hidden_layers": 5,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.29.0.dev0",
|
24 |
+
"vocab_size": 1000
|
25 |
+
}
|
checkpoint-150/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d138721b88db7b12c6077706e0d39f7bed7ed83cabcd34c0b53d6d1e916efbb
|
3 |
+
size 302896
|
checkpoint-150/unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"_name_or_path": "dog-example-demo/checkpoint-100",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": 8,
|
9 |
+
"block_out_channels": [
|
10 |
+
32,
|
11 |
+
64
|
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": 32,
|
19 |
+
"cross_attention_norm": null,
|
20 |
+
"down_block_types": [
|
21 |
+
"DownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D"
|
23 |
+
],
|
24 |
+
"downsample_padding": 1,
|
25 |
+
"dropout": 0.0,
|
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": 32,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_act_fn": null,
|
47 |
+
"time_embedding_dim": null,
|
48 |
+
"time_embedding_type": "positional",
|
49 |
+
"timestep_post_act": null,
|
50 |
+
"up_block_types": [
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"UpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
checkpoint-150/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0cfb6dcc7fb590ddf341e26397e8f86314f7895cbf94778133160fa157c7a26
|
3 |
+
size 5834433
|
checkpoint-20/optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1848f8071a0dbd914e6070b264305d8c599d27425553d9e82387017921f7707a
|
3 |
+
size 12286505
|
checkpoint-20/random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14663
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4574e9d682bb8812cd6059a60d29cf654c5183464bb9f03123650ab3e63f89a1
|
3 |
size 14663
|
checkpoint-20/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hf-internal-testing/tiny-stable-diffusion-pipe",
|
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": 32,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 37,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 4,
|
19 |
+
"num_hidden_layers": 5,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.29.0.dev0",
|
24 |
+
"vocab_size": 1000
|
25 |
+
}
|
checkpoint-20/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cdbba29f15a5d16f8619b61d0dc7d456ac63a86a6baee9a984b4c39c0850a85
|
3 |
+
size 302896
|
checkpoint-20/unet/config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.17.0.dev0",
|
4 |
+
"_name_or_path": "hf-internal-testing/tiny-stable-diffusion-pipe",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": 8,
|
9 |
+
"block_out_channels": [
|
10 |
+
32,
|
11 |
+
64
|
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": 32,
|
19 |
+
"cross_attention_norm": null,
|
20 |
+
"down_block_types": [
|
21 |
+
"DownBlock2D",
|
22 |
+
"CrossAttnDownBlock2D"
|
23 |
+
],
|
24 |
+
"downsample_padding": 1,
|
25 |
+
"dropout": 0.0,
|
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": 32,
|
45 |
+
"time_cond_proj_dim": null,
|
46 |
+
"time_embedding_act_fn": null,
|
47 |
+
"time_embedding_dim": null,
|
48 |
+
"time_embedding_type": "positional",
|
49 |
+
"timestep_post_act": null,
|
50 |
+
"up_block_types": [
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"UpBlock2D"
|
53 |
+
],
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": false
|
56 |
+
}
|
checkpoint-20/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05182b23370a76acd878b981cf271cc37a789f2c36077bf9202187d3b5a43be0
|
3 |
+
size 5834433
|
checkpoint-30/optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:390ac15586c84bbd8698336cc2624363a5bfaa47146bb80771f885877deee37c
|
3 |
+
size 12286505
|