nishant-glance
commited on
Commit
•
538fd33
1
Parent(s):
17407b0
End of training
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +22 -0
- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/random_states_0.pkl +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.safetensors +3 -0
- checkpoint-1500/optimizer.bin +3 -0
- checkpoint-1500/random_states_0.pkl +3 -0
- checkpoint-1500/scheduler.bin +3 -0
- checkpoint-1500/text_encoder/config.json +25 -0
- checkpoint-1500/text_encoder/pytorch_model.bin +3 -0
- checkpoint-1500/unet/config.json +66 -0
- checkpoint-1500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-2000/optimizer.bin +3 -0
- checkpoint-2000/random_states_0.pkl +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.safetensors +3 -0
- checkpoint-2500/optimizer.bin +3 -0
- checkpoint-2500/random_states_0.pkl +3 -0
- checkpoint-2500/scheduler.bin +3 -0
- checkpoint-2500/text_encoder/config.json +25 -0
- checkpoint-2500/text_encoder/pytorch_model.bin +3 -0
- checkpoint-2500/unet/config.json +66 -0
- checkpoint-2500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-3000/optimizer.bin +3 -0
- checkpoint-3000/random_states_0.pkl +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.safetensors +3 -0
- checkpoint-3500/optimizer.bin +3 -0
- checkpoint-3500/random_states_0.pkl +3 -0
- checkpoint-3500/scheduler.bin +3 -0
- checkpoint-3500/text_encoder/config.json +25 -0
- checkpoint-3500/text_encoder/pytorch_model.bin +3 -0
- checkpoint-3500/unet/config.json +66 -0
- checkpoint-3500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-500/optimizer.bin +3 -0
- checkpoint-500/random_states_0.pkl +3 -0
- checkpoint-500/scheduler.bin +3 -0
- checkpoint-500/text_encoder/config.json +25 -0
- checkpoint-500/text_encoder/pytorch_model.bin +3 -0
- checkpoint-500/unet/config.json +66 -0
- checkpoint-500/unet/diffusion_pytorch_model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
license: creativeml-openrail-m
|
4 |
+
base_model: CompVis/stable-diffusion-v1-4
|
5 |
+
instance_prompt: a photo of yqg person
|
6 |
+
tags:
|
7 |
+
- stable-diffusion
|
8 |
+
- stable-diffusion-diffusers
|
9 |
+
- text-to-image
|
10 |
+
- diffusers
|
11 |
+
- dreambooth
|
12 |
+
inference: true
|
13 |
+
---
|
14 |
+
|
15 |
+
# DreamBooth - nishant-glance/model-sd-1-4-priorp-unet-3600-lr2e-new
|
16 |
+
|
17 |
+
This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of yqg person 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-1000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a035196d9045246a4d4fea8b8fa6b6a6197c1d4be0c58bacc57ae38594f2745
|
3 |
+
size 7861403191
|
checkpoint-1000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71b8e655549ec3780f8c176dcfd5a4bf3dde2451b475ac7a223961161140a2a1
|
3 |
+
size 15691
|
checkpoint-1000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8d2c0a0399fe7c06785ee1e166ec0e0678cfcb17028d6a471b0674a4e4b0957
|
3 |
+
size 563
|
checkpoint-1000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.32.0",
|
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:df22df26d6eebf82e3908752f1d266e93c49dafb95e2e3809144805f25929d03
|
3 |
+
size 492308829
|
checkpoint-1000/unet/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.21.0.dev0",
|
4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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 |
+
"dual_cross_attention": false,
|
32 |
+
"encoder_hid_dim": null,
|
33 |
+
"encoder_hid_dim_type": null,
|
34 |
+
"flip_sin_to_cos": true,
|
35 |
+
"freq_shift": 0,
|
36 |
+
"in_channels": 4,
|
37 |
+
"layers_per_block": 2,
|
38 |
+
"mid_block_only_cross_attention": null,
|
39 |
+
"mid_block_scale_factor": 1,
|
40 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
41 |
+
"norm_eps": 1e-05,
|
42 |
+
"norm_num_groups": 32,
|
43 |
+
"num_attention_heads": null,
|
44 |
+
"num_class_embeds": null,
|
45 |
+
"only_cross_attention": false,
|
46 |
+
"out_channels": 4,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 64,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"transformer_layers_per_block": 1,
|
58 |
+
"up_block_types": [
|
59 |
+
"UpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D"
|
63 |
+
],
|
64 |
+
"upcast_attention": false,
|
65 |
+
"use_linear_projection": false
|
66 |
+
}
|
checkpoint-1000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08264e672e5575eb25297168ed54f941f2be2fe0f55a04867145dba446a0769a
|
3 |
+
size 3438167536
|
checkpoint-1500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de279ca38a370f049726df465dd0b9a5c1f8e2ca4f73e3927cda614bf2a56614
|
3 |
+
size 7861403191
|
checkpoint-1500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d667133aee110e71cbae40f3dc7a64cf6f52eb6c9bbfb697e5406ef68c57ea4
|
3 |
+
size 15691
|
checkpoint-1500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46243d0b698c53230e0f4c18f0c6a8fc397a1a8994ed86c85da43720acaf01f1
|
3 |
+
size 563
|
checkpoint-1500/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.32.0",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
checkpoint-1500/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54ab05a3e69488025ee11919e0b818014459b2830312f2fa9715711cb07071c0
|
3 |
+
size 492308829
|
checkpoint-1500/unet/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.21.0.dev0",
|
4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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 |
+
"dual_cross_attention": false,
|
32 |
+
"encoder_hid_dim": null,
|
33 |
+
"encoder_hid_dim_type": null,
|
34 |
+
"flip_sin_to_cos": true,
|
35 |
+
"freq_shift": 0,
|
36 |
+
"in_channels": 4,
|
37 |
+
"layers_per_block": 2,
|
38 |
+
"mid_block_only_cross_attention": null,
|
39 |
+
"mid_block_scale_factor": 1,
|
40 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
41 |
+
"norm_eps": 1e-05,
|
42 |
+
"norm_num_groups": 32,
|
43 |
+
"num_attention_heads": null,
|
44 |
+
"num_class_embeds": null,
|
45 |
+
"only_cross_attention": false,
|
46 |
+
"out_channels": 4,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 64,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"transformer_layers_per_block": 1,
|
58 |
+
"up_block_types": [
|
59 |
+
"UpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D"
|
63 |
+
],
|
64 |
+
"upcast_attention": false,
|
65 |
+
"use_linear_projection": false
|
66 |
+
}
|
checkpoint-1500/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca7924877239e74e2c5f110f658b10c168b0887865a449067b728bfa22671024
|
3 |
+
size 3438167536
|
checkpoint-2000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e599f910685ba95068a373a8f7865ed072d8c3d6e43979ec2fa46efd533816a
|
3 |
+
size 7861403191
|
checkpoint-2000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9120ecf68c5758ba64749a50ab14ff5a594fac435a737df4aa7a38b198c4a7fa
|
3 |
+
size 15691
|
checkpoint-2000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bb56567eea0c57010cdd1c9084a5b676eb47733aa9450fa521ee58bd169ecfe
|
3 |
+
size 563
|
checkpoint-2000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.32.0",
|
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:b7fd829dc9525a2afdc573e62fd315504049b1c75650273abea456ded0122549
|
3 |
+
size 492308829
|
checkpoint-2000/unet/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.21.0.dev0",
|
4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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 |
+
"dual_cross_attention": false,
|
32 |
+
"encoder_hid_dim": null,
|
33 |
+
"encoder_hid_dim_type": null,
|
34 |
+
"flip_sin_to_cos": true,
|
35 |
+
"freq_shift": 0,
|
36 |
+
"in_channels": 4,
|
37 |
+
"layers_per_block": 2,
|
38 |
+
"mid_block_only_cross_attention": null,
|
39 |
+
"mid_block_scale_factor": 1,
|
40 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
41 |
+
"norm_eps": 1e-05,
|
42 |
+
"norm_num_groups": 32,
|
43 |
+
"num_attention_heads": null,
|
44 |
+
"num_class_embeds": null,
|
45 |
+
"only_cross_attention": false,
|
46 |
+
"out_channels": 4,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 64,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"transformer_layers_per_block": 1,
|
58 |
+
"up_block_types": [
|
59 |
+
"UpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D"
|
63 |
+
],
|
64 |
+
"upcast_attention": false,
|
65 |
+
"use_linear_projection": false
|
66 |
+
}
|
checkpoint-2000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a6d0e1410e31210a79ddea23030f15173426aa797348b86a07f3ecaebd720f5
|
3 |
+
size 3438167536
|
checkpoint-2500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:169d60f57493e638a5d8a9a9d9da2bbb19ab81fdcd89252971c0684b49b8dc77
|
3 |
+
size 7861403191
|
checkpoint-2500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10e2a5d086a6f8d1ccae7461e9e1347c4be7255e4a6066c2a6522cbbfb90d68d
|
3 |
+
size 15691
|
checkpoint-2500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a152e5b821f34e21bf51d02e838823b194bf71dc670f6ce3ef70aebdf7626c36
|
3 |
+
size 563
|
checkpoint-2500/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.32.0",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
checkpoint-2500/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7e08db3b5b657e55ca686895e4e17b5911a4c8571b89603cd4d5e3535edfb4e
|
3 |
+
size 492308829
|
checkpoint-2500/unet/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.21.0.dev0",
|
4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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 |
+
"dual_cross_attention": false,
|
32 |
+
"encoder_hid_dim": null,
|
33 |
+
"encoder_hid_dim_type": null,
|
34 |
+
"flip_sin_to_cos": true,
|
35 |
+
"freq_shift": 0,
|
36 |
+
"in_channels": 4,
|
37 |
+
"layers_per_block": 2,
|
38 |
+
"mid_block_only_cross_attention": null,
|
39 |
+
"mid_block_scale_factor": 1,
|
40 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
41 |
+
"norm_eps": 1e-05,
|
42 |
+
"norm_num_groups": 32,
|
43 |
+
"num_attention_heads": null,
|
44 |
+
"num_class_embeds": null,
|
45 |
+
"only_cross_attention": false,
|
46 |
+
"out_channels": 4,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 64,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"transformer_layers_per_block": 1,
|
58 |
+
"up_block_types": [
|
59 |
+
"UpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D"
|
63 |
+
],
|
64 |
+
"upcast_attention": false,
|
65 |
+
"use_linear_projection": false
|
66 |
+
}
|
checkpoint-2500/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c24ced4fa50323f2961e9390b428acfebdc909bccd698ae48c60a2a45c143a07
|
3 |
+
size 3438167536
|
checkpoint-3000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9264bcb88c56a010ae31569a8778574426aa0b57e11c2655904af61841718af7
|
3 |
+
size 7861403191
|
checkpoint-3000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f02904cc641ada1a41a2c6035088e6ef3e28c30b1fe63dbb122f80631a61399
|
3 |
+
size 15691
|
checkpoint-3000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c376297ecb8911fbef9861a0bc59cc1906545cf70e6b276f15a376c8380b888
|
3 |
+
size 563
|
checkpoint-3000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.32.0",
|
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:f17a6621350e39e4242156586cfc4ae65a2812811480e0bdc4e45f8f9241097b
|
3 |
+
size 492308829
|
checkpoint-3000/unet/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.21.0.dev0",
|
4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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 |
+
"dual_cross_attention": false,
|
32 |
+
"encoder_hid_dim": null,
|
33 |
+
"encoder_hid_dim_type": null,
|
34 |
+
"flip_sin_to_cos": true,
|
35 |
+
"freq_shift": 0,
|
36 |
+
"in_channels": 4,
|
37 |
+
"layers_per_block": 2,
|
38 |
+
"mid_block_only_cross_attention": null,
|
39 |
+
"mid_block_scale_factor": 1,
|
40 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
41 |
+
"norm_eps": 1e-05,
|
42 |
+
"norm_num_groups": 32,
|
43 |
+
"num_attention_heads": null,
|
44 |
+
"num_class_embeds": null,
|
45 |
+
"only_cross_attention": false,
|
46 |
+
"out_channels": 4,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 64,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"transformer_layers_per_block": 1,
|
58 |
+
"up_block_types": [
|
59 |
+
"UpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D"
|
63 |
+
],
|
64 |
+
"upcast_attention": false,
|
65 |
+
"use_linear_projection": false
|
66 |
+
}
|
checkpoint-3000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18d8bc4c4f6786a08cb4a223202e0fe5cf50c81087b48f6f009b81408ecbe2a7
|
3 |
+
size 3438167536
|
checkpoint-3500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18b149ee8744f6280efedc1c1d0d9aca6c88ff96da6bcdde788f93ca78d307b8
|
3 |
+
size 7861403191
|
checkpoint-3500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00b0b9a463390004aab04fb0f1e7414cff2b25e6cd7ca37f8e9fecc0e0a31dd7
|
3 |
+
size 15691
|
checkpoint-3500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fea83ff14f5e8f1da2235cf21ca8b3fdc5fd812f31508a5c7359633540e54ac7
|
3 |
+
size 563
|
checkpoint-3500/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.32.0",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
checkpoint-3500/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca53d1836b55085ed247385c2e85d4b07bedd928dc32c64c1bb9a25da7284ad3
|
3 |
+
size 492308829
|
checkpoint-3500/unet/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.21.0.dev0",
|
4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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 |
+
"dual_cross_attention": false,
|
32 |
+
"encoder_hid_dim": null,
|
33 |
+
"encoder_hid_dim_type": null,
|
34 |
+
"flip_sin_to_cos": true,
|
35 |
+
"freq_shift": 0,
|
36 |
+
"in_channels": 4,
|
37 |
+
"layers_per_block": 2,
|
38 |
+
"mid_block_only_cross_attention": null,
|
39 |
+
"mid_block_scale_factor": 1,
|
40 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
41 |
+
"norm_eps": 1e-05,
|
42 |
+
"norm_num_groups": 32,
|
43 |
+
"num_attention_heads": null,
|
44 |
+
"num_class_embeds": null,
|
45 |
+
"only_cross_attention": false,
|
46 |
+
"out_channels": 4,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 64,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"transformer_layers_per_block": 1,
|
58 |
+
"up_block_types": [
|
59 |
+
"UpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D"
|
63 |
+
],
|
64 |
+
"upcast_attention": false,
|
65 |
+
"use_linear_projection": false
|
66 |
+
}
|
checkpoint-3500/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:940d4007f9f9ff83e17e768a95770a809fc11c74e8fc847dcd749f652cb34293
|
3 |
+
size 3438167536
|
checkpoint-500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66104e73196cdd9ee85ada68b26fd667cd41d7c3cf44cc0234a5b97af78dd546
|
3 |
+
size 7861403191
|
checkpoint-500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f29433e895960b33f162ee294e42c42a1ac7f68ceeb25cf1660acf9ba76d79f0
|
3 |
+
size 15691
|
checkpoint-500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8830559ab171cd874e82f050b76fb65bbc856afae8205880f7b2afac6849b09
|
3 |
+
size 563
|
checkpoint-500/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.32.0",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
checkpoint-500/text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b9a3ef60715daa672d29784435fdefcc86556151b223a6db028eb6f2aeca65a
|
3 |
+
size 492308829
|
checkpoint-500/unet/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.21.0.dev0",
|
4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
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 |
+
"dual_cross_attention": false,
|
32 |
+
"encoder_hid_dim": null,
|
33 |
+
"encoder_hid_dim_type": null,
|
34 |
+
"flip_sin_to_cos": true,
|
35 |
+
"freq_shift": 0,
|
36 |
+
"in_channels": 4,
|
37 |
+
"layers_per_block": 2,
|
38 |
+
"mid_block_only_cross_attention": null,
|
39 |
+
"mid_block_scale_factor": 1,
|
40 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
41 |
+
"norm_eps": 1e-05,
|
42 |
+
"norm_num_groups": 32,
|
43 |
+
"num_attention_heads": null,
|
44 |
+
"num_class_embeds": null,
|
45 |
+
"only_cross_attention": false,
|
46 |
+
"out_channels": 4,
|
47 |
+
"projection_class_embeddings_input_dim": null,
|
48 |
+
"resnet_out_scale_factor": 1.0,
|
49 |
+
"resnet_skip_time_act": false,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"sample_size": 64,
|
52 |
+
"time_cond_proj_dim": null,
|
53 |
+
"time_embedding_act_fn": null,
|
54 |
+
"time_embedding_dim": null,
|
55 |
+
"time_embedding_type": "positional",
|
56 |
+
"timestep_post_act": null,
|
57 |
+
"transformer_layers_per_block": 1,
|
58 |
+
"up_block_types": [
|
59 |
+
"UpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D"
|
63 |
+
],
|
64 |
+
"upcast_attention": false,
|
65 |
+
"use_linear_projection": false
|
66 |
+
}
|
checkpoint-500/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54398d9d2b3adbf5b319c6accf27651d27028c1297405d6dbc744c7366eea930
|
3 |
+
size 3438167536
|