nishant-glance
commited on
Commit
·
ad85e77
1
Parent(s):
eef6095
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-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
- feature_extractor/preprocessor_config.json +28 -0
- logs/dreambooth/1692981371.4012005/events.out.tfevents.1692981371.glancefeed-nishant-oli-gpu-large.131218.1 +3 -0
- logs/dreambooth/1692981371.4028254/hparams.yml +58 -0
- logs/dreambooth/1692981905.709793/events.out.tfevents.1692981905.glancefeed-nishant-oli-gpu-large.136473.1 +3 -0
- logs/dreambooth/1692981905.7114775/hparams.yml +58 -0
- logs/dreambooth/1692982005.72652/events.out.tfevents.1692982005.glancefeed-nishant-oli-gpu-large.136792.1 +3 -0
- logs/dreambooth/1692982005.7282681/hparams.yml +58 -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 sks woman
|
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-3000-lowlr-regnam2
|
16 |
+
|
17 |
+
This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks woman 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:ffda20f39e90e279a5d056f1aa48c96d3b297e2c9451b0f97c883e38c99649d2
|
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 sha256:6dc67474a1f3ec2a6656c3aba01b503b6a7986d25fd4fec9d1b38a947e10fc84
|
3 |
+
size 15691
|
checkpoint-1000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:223436be2788dc84d53d2c2e4303ade14df55ba01000214c925cafe35a59ad75
|
3 |
+
size 563
|
checkpoint-1000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "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 sha256:490ad34b8218a96fa2c0a8cb56e2503e62646799bcec8af645b894829cd6d808
|
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 sha256:774c3e0258da05fbc9232528a9fe0e4a3bbe569c65a3b155f78495ec3c85a35e
|
3 |
+
size 3438167536
|
checkpoint-1500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4d62e6d635b0018ece0d8f7d4ee05d47dda90615ed6f410be714e24433e17d1
|
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 sha256:60ffdf55ae01b39250f63cef29a2dbbe4f6b2e6a0d22d2a87e83050c43eb65fe
|
3 |
+
size 15691
|
checkpoint-1500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7be764cabe8a7de848698b3c50662a14a6678e140228a345f6150b6286c7a070
|
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 sha256:637fc1df51881ba418733447998167b443eee7691080b1a3fb1183148082ebaa
|
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:ac2bf3e2027dcf534eeaf7a5f39ed6151f00678c699466adf2cbc42cdbf2ef3f
|
3 |
+
size 3438167536
|
checkpoint-2000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:664bb4031a16679a3dd1ae94c145d8c2030bd6e28db1d1271d9bc5ba74f50733
|
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:a3683bec6ec769a0d1166f6d720b7a43d3bb9f2f846e0863f8e95ab296fd8c6d
|
3 |
+
size 15691
|
checkpoint-2000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb4f0b1924463e34e3dc4a27e2ebe7ee7a43bc8be36d5cff2a75500ff628d083
|
3 |
+
size 563
|
checkpoint-2000/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "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 sha256:0c47607a7f03ab60439c939ad073b27b1ed5020a5d33af95632ff788a5c36d8e
|
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 sha256:35446877070c4de1d7900965ffe4fae6ae225506633f7188da1cacd39e61b0b7
|
3 |
+
size 3438167536
|
checkpoint-2500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c41697d9195adf4fb8327b289d28cce503daf20d01f95cf118bd22b85175e01
|
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:bb55307aef2e3920ee99db3dc96b2b5eab572669ed0e2d610ff6eec7f6e522a1
|
3 |
+
size 15691
|
checkpoint-2500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc0c7a75e7ae7f4c274beea718ef57c0183f34532a7b2d1204d53c83dc6c83da
|
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 sha256:9f8ac592f678d8f9e5c0559fd43dbbb645967e1711c6b64c12b328d981e94fb9
|
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:e4b235c91a568f6f8586bd5c4505115e148fb733b1dfa7e71fab8dd5312a8fb1
|
3 |
+
size 3438167536
|
checkpoint-3000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51893483bdc1a8ddc01cfa244b948372b546417161ee78d60c4e4be63f4ec51a
|
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:e99ee772d4f91957068b2389d33dcc682f58233ee7930eca20e348abbf67d4a5
|
3 |
+
size 15691
|
checkpoint-3000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2045310aaf65b27b6e6ead5f219951d64b6a5501ced0aba650be82bfb33d51a6
|
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 sha256:869c7c5a68f6410f3589f58b75fa65c4b78be413dfc330c9816a4f185c254b86
|
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 sha256:30fdc0633cc730daf4d71c47d7a55177c486229713eeb66257d98f112d632c26
|
3 |
+
size 3438167536
|
checkpoint-500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b91cc381b6362f429079fc56ea9961de92e7fa611693f15f579ca9a91b1f8b3
|
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 sha256:29d45542ae32a54a834a123ccd68d2baeb0cd7ae0757574596e7af79bf45436c
|
3 |
+
size 15691
|
checkpoint-500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8b7809f518a96a4fa4069f707e8433d0ae60949b56c65c39b0a64950d711aeb
|
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 sha256:96e8590e566971114515cfd7c7f0212f3487a0640d325adf6dd556c75abba673
|
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 sha256:93b91f1d2a727146485617c7f500c6f6f22c5a3951b343b6d649674aa50ecb17
|
3 |
+
size 3438167536
|
feature_extractor/preprocessor_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 224,
|
4 |
+
"width": 224
|
5 |
+
},
|
6 |
+
"do_center_crop": true,
|
7 |
+
"do_convert_rgb": true,
|
8 |
+
"do_normalize": true,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"feature_extractor_type": "CLIPFeatureExtractor",
|
12 |
+
"image_mean": [
|
13 |
+
0.48145466,
|
14 |
+
0.4578275,
|
15 |
+
0.40821073
|
16 |
+
],
|
17 |
+
"image_processor_type": "CLIPImageProcessor",
|
18 |
+
"image_std": [
|
19 |
+
0.26862954,
|
20 |
+
0.26130258,
|
21 |
+
0.27577711
|
22 |
+
],
|
23 |
+
"resample": 3,
|
24 |
+
"rescale_factor": 0.00392156862745098,
|
25 |
+
"size": {
|
26 |
+
"shortest_edge": 224
|
27 |
+
}
|
28 |
+
}
|
logs/dreambooth/1692981371.4012005/events.out.tfevents.1692981371.glancefeed-nishant-oli-gpu-large.131218.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b03f51e4cebe11925cb66a0956d6c3820bdd438815c3559545a291d4d3ea4d8d
|
3 |
+
size 2922
|
logs/dreambooth/1692981371.4028254/hparams.yml
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
class_data_dir: class-sd-1-4-priorp-unet-3000-lowlr-regnam2
|
10 |
+
class_labels_conditioning: null
|
11 |
+
class_prompt: a photo of woman
|
12 |
+
dataloader_num_workers: 0
|
13 |
+
enable_xformers_memory_efficient_attention: false
|
14 |
+
gradient_accumulation_steps: 1
|
15 |
+
gradient_checkpointing: true
|
16 |
+
hub_model_id: null
|
17 |
+
hub_token: null
|
18 |
+
instance_data_dir: radhika
|
19 |
+
instance_prompt: a photo of sks woman
|
20 |
+
learning_rate: 1.0e-06
|
21 |
+
local_rank: 0
|
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: 3000
|
29 |
+
mixed_precision: null
|
30 |
+
num_class_images: 2400
|
31 |
+
num_train_epochs: 3
|
32 |
+
num_validation_images: 4
|
33 |
+
offset_noise: false
|
34 |
+
output_dir: model-sd-1-4-priorp-unet-3000-lowlr-regnam2
|
35 |
+
pre_compute_text_embeddings: false
|
36 |
+
pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
|
37 |
+
prior_generation_precision: null
|
38 |
+
prior_loss_weight: 1.0
|
39 |
+
push_to_hub: true
|
40 |
+
report_to: tensorboard
|
41 |
+
resolution: 512
|
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 |
+
text_encoder_use_attention_mask: false
|
50 |
+
tokenizer_max_length: null
|
51 |
+
tokenizer_name: null
|
52 |
+
train_batch_size: 1
|
53 |
+
train_text_encoder: true
|
54 |
+
use_8bit_adam: false
|
55 |
+
validation_prompt: null
|
56 |
+
validation_scheduler: DPMSolverMultistepScheduler
|
57 |
+
validation_steps: 100
|
58 |
+
with_prior_preservation: true
|
logs/dreambooth/1692981905.709793/events.out.tfevents.1692981905.glancefeed-nishant-oli-gpu-large.136473.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:150d70ac9202898fbcb013fe9f573d9fd28927ccee8f107e74ab9bd345a87ce0
|
3 |
+
size 2922
|
logs/dreambooth/1692981905.7114775/hparams.yml
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
class_data_dir: class-sd-1-4-priorp-unet-3000-lowlr-regnam2
|
10 |
+
class_labels_conditioning: null
|
11 |
+
class_prompt: a photo of woman
|
12 |
+
dataloader_num_workers: 0
|
13 |
+
enable_xformers_memory_efficient_attention: false
|
14 |
+
gradient_accumulation_steps: 1
|
15 |
+
gradient_checkpointing: true
|
16 |
+
hub_model_id: null
|
17 |
+
hub_token: null
|
18 |
+
instance_data_dir: radhika
|
19 |
+
instance_prompt: a photo of sks woman
|
20 |
+
learning_rate: 1.0e-06
|
21 |
+
local_rank: 0
|
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: 3000
|
29 |
+
mixed_precision: null
|
30 |
+
num_class_images: 2400
|
31 |
+
num_train_epochs: 3
|
32 |
+
num_validation_images: 4
|
33 |
+
offset_noise: false
|
34 |
+
output_dir: model-sd-1-4-priorp-unet-3000-lowlr-regnam2
|
35 |
+
pre_compute_text_embeddings: false
|
36 |
+
pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
|
37 |
+
prior_generation_precision: null
|
38 |
+
prior_loss_weight: 1.0
|
39 |
+
push_to_hub: true
|
40 |
+
report_to: tensorboard
|
41 |
+
resolution: 512
|
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 |
+
text_encoder_use_attention_mask: false
|
50 |
+
tokenizer_max_length: null
|
51 |
+
tokenizer_name: null
|
52 |
+
train_batch_size: 1
|
53 |
+
train_text_encoder: true
|
54 |
+
use_8bit_adam: false
|
55 |
+
validation_prompt: null
|
56 |
+
validation_scheduler: DPMSolverMultistepScheduler
|
57 |
+
validation_steps: 100
|
58 |
+
with_prior_preservation: true
|
logs/dreambooth/1692982005.72652/events.out.tfevents.1692982005.glancefeed-nishant-oli-gpu-large.136792.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:077b8628b1bf6ff53eec03280eb03d5cc40f06244885e08793e3e35c9c50d3b8
|
3 |
+
size 2922
|
logs/dreambooth/1692982005.7282681/hparams.yml
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
class_data_dir: class-sd-1-4-priorp-unet-3000-lowlr-regnam2
|
10 |
+
class_labels_conditioning: null
|
11 |
+
class_prompt: a photo of woman
|
12 |
+
dataloader_num_workers: 0
|
13 |
+
enable_xformers_memory_efficient_attention: false
|
14 |
+
gradient_accumulation_steps: 1
|
15 |
+
gradient_checkpointing: true
|
16 |
+
hub_model_id: null
|
17 |
+
hub_token: null
|
18 |
+
instance_data_dir: radhika
|
19 |
+
instance_prompt: a photo of sks woman
|
20 |
+
learning_rate: 1.0e-06
|
21 |
+
local_rank: 0
|
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: 3000
|
29 |
+
mixed_precision: null
|
30 |
+
num_class_images: 2400
|
31 |
+
num_train_epochs: 3
|
32 |
+
num_validation_images: 4
|
33 |
+
offset_noise: false
|
34 |
+
output_dir: model-sd-1-4-priorp-unet-3000-lowlr-regnam2
|
35 |
+
pre_compute_text_embeddings: false
|
36 |
+
pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
|
37 |
+
prior_generation_precision: null
|
38 |
+
prior_loss_weight: 1.0
|
39 |
+
push_to_hub: true
|
40 |
+
report_to: tensorboard
|
41 |
+
resolution: 512
|
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 |
+
text_encoder_use_attention_mask: false
|
50 |
+
tokenizer_max_length: null
|
51 |
+
tokenizer_name: null
|
52 |
+
train_batch_size: 1
|
53 |
+
train_text_encoder: true
|
54 |
+
use_8bit_adam: false
|
55 |
+
validation_prompt: null
|
56 |
+
validation_scheduler: DPMSolverMultistepScheduler
|
57 |
+
validation_steps: 100
|
58 |
+
with_prior_preservation: true
|