sang-kyung commited on
Commit
0c7f1bd
1 Parent(s): 5b01464

End of training

Browse files
README.md CHANGED
@@ -1,7 +1,7 @@
1
 
2
  ---
3
  license: creativeml-openrail-m
4
- base_model: CompVis/stable-diffusion-v1-4
5
  instance_prompt: a photo of sks bottle
6
  tags:
7
  - stable-diffusion
@@ -14,7 +14,7 @@ inference: true
14
 
15
  # DreamBooth - sang-kyung/bottle
16
 
17
- This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks bottle using [DreamBooth](https://dreambooth.github.io/).
18
  You can find some example images in the following.
19
 
20
 
 
1
 
2
  ---
3
  license: creativeml-openrail-m
4
+ base_model: stabilityai/stable-diffusion-2-1-base
5
  instance_prompt: a photo of sks bottle
6
  tags:
7
  - stable-diffusion
 
14
 
15
  # DreamBooth - sang-kyung/bottle
16
 
17
+ This is a dreambooth model derived from stabilityai/stable-diffusion-2-1-base. The weights were trained on a photo of sks bottle using [DreamBooth](https://dreambooth.github.io/).
18
  You can find some example images in the following.
19
 
20
 
checkpoint-1000/optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5becd0455483d94eb17c684e71816d34e7235500f41c0b76b26e86173041a63
3
- size 1972599009
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99314dcca511c7398a2e2516761134cd541f2ece3b4c0a4f3a0baf092adbce9b
3
+ size 2421618099
checkpoint-1000/random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3effc7aca99212cfeabf890d34de26868534158acb05c49ceeac207d92f5c4ef
3
- size 14599
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2486617d0529b5beaeb6692cb18ac78fade44157f4e780d34285031af1ae88ec
3
+ size 14663
checkpoint-1000/text_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "CompVis/stable-diffusion-v1-4",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -7,16 +7,16 @@
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",
 
1
  {
2
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
 
7
  "bos_token_id": 0,
8
  "dropout": 0.0,
9
  "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 1024,
12
  "initializer_factor": 1.0,
13
  "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
  "layer_norm_eps": 1e-05,
16
  "max_position_embeddings": 77,
17
  "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
  "torch_dtype": "float32",
checkpoint-1000/text_encoder/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88be113e2506d41ca1ee236ed9cf3a6cd69d2c8ed5c1d8b3a64cb7564a6e1e72
3
- size 492309793
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d45afc20d6a749b59a40d9ebe14fa3a5b80bd95eaa34637df324079404b68b3
3
+ size 1361679905
checkpoint-1000/unet/config.json CHANGED
@@ -1,11 +1,16 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.18.0.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
- "attention_head_dim": 8,
 
 
 
 
 
9
  "block_out_channels": [
10
  320,
11
  640,
@@ -17,7 +22,7 @@
17
  "class_embeddings_concat": false,
18
  "conv_in_kernel": 3,
19
  "conv_out_kernel": 3,
20
- "cross_attention_dim": 768,
21
  "cross_attention_norm": null,
22
  "down_block_types": [
23
  "CrossAttnDownBlock2D",
@@ -59,5 +64,5 @@
59
  "CrossAttnUpBlock2D"
60
  ],
61
  "upcast_attention": false,
62
- "use_linear_projection": false
63
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
5
  "act_fn": "silu",
6
  "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
8
+ "attention_head_dim": [
9
+ 5,
10
+ 10,
11
+ 20,
12
+ 20
13
+ ],
14
  "block_out_channels": [
15
  320,
16
  640,
 
22
  "class_embeddings_concat": false,
23
  "conv_in_kernel": 3,
24
  "conv_out_kernel": 3,
25
+ "cross_attention_dim": 1024,
26
  "cross_attention_norm": null,
27
  "down_block_types": [
28
  "CrossAttnDownBlock2D",
 
64
  "CrossAttnUpBlock2D"
65
  ],
66
  "upcast_attention": false,
67
+ "use_linear_projection": true
68
  }
checkpoint-1000/unet/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b58df0ed65c00d475f885d337bf961b28e760a0865ef15c3a80fdf1830838ce
3
- size 3438375973
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f704762e648813d38c085f9254f379915790d8b4c7bb956cadfce8a4203e3dec
3
+ size 3463934693
model_index.json CHANGED
@@ -5,10 +5,10 @@
5
  "transformers",
6
  "CLIPImageProcessor"
7
  ],
8
- "requires_safety_checker": true,
9
  "safety_checker": [
10
- "stable_diffusion",
11
- "StableDiffusionSafetyChecker"
12
  ],
13
  "scheduler": [
14
  "diffusers",
 
5
  "transformers",
6
  "CLIPImageProcessor"
7
  ],
8
+ "requires_safety_checker": false,
9
  "safety_checker": [
10
+ null,
11
+ null
12
  ],
13
  "scheduler": [
14
  "diffusers",
text_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "CompVis/stable-diffusion-v1-4",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -7,16 +7,16 @@
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",
 
1
  {
2
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
 
7
  "bos_token_id": 0,
8
  "dropout": 0.0,
9
  "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 1024,
12
  "initializer_factor": 1.0,
13
  "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
  "layer_norm_eps": 1e-05,
16
  "max_position_embeddings": 77,
17
  "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
  "torch_dtype": "float32",
text_encoder/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88be113e2506d41ca1ee236ed9cf3a6cd69d2c8ed5c1d8b3a64cb7564a6e1e72
3
- size 492309793
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d45afc20d6a749b59a40d9ebe14fa3a5b80bd95eaa34637df324079404b68b3
3
+ size 1361679905
tokenizer/special_tokens_map.json CHANGED
@@ -13,7 +13,7 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|endoftext|>",
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "!",
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
unet/config.json CHANGED
@@ -1,11 +1,16 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.18.0.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
- "attention_head_dim": 8,
 
 
 
 
 
9
  "block_out_channels": [
10
  320,
11
  640,
@@ -17,7 +22,7 @@
17
  "class_embeddings_concat": false,
18
  "conv_in_kernel": 3,
19
  "conv_out_kernel": 3,
20
- "cross_attention_dim": 768,
21
  "cross_attention_norm": null,
22
  "down_block_types": [
23
  "CrossAttnDownBlock2D",
@@ -59,5 +64,5 @@
59
  "CrossAttnUpBlock2D"
60
  ],
61
  "upcast_attention": false,
62
- "use_linear_projection": false
63
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
5
  "act_fn": "silu",
6
  "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
8
+ "attention_head_dim": [
9
+ 5,
10
+ 10,
11
+ 20,
12
+ 20
13
+ ],
14
  "block_out_channels": [
15
  320,
16
  640,
 
22
  "class_embeddings_concat": false,
23
  "conv_in_kernel": 3,
24
  "conv_out_kernel": 3,
25
+ "cross_attention_dim": 1024,
26
  "cross_attention_norm": null,
27
  "down_block_types": [
28
  "CrossAttnDownBlock2D",
 
64
  "CrossAttnUpBlock2D"
65
  ],
66
  "upcast_attention": false,
67
+ "use_linear_projection": true
68
  }
unet/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b58df0ed65c00d475f885d337bf961b28e760a0865ef15c3a80fdf1830838ce
3
- size 3438375973
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f704762e648813d38c085f9254f379915790d8b4c7bb956cadfce8a4203e3dec
3
+ size 3463934693
vae/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.18.0.dev0",
4
- "_name_or_path": "/home/sangkyung/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/59ec6bdf37d6279d3c0faf36e89ff1aa34f7ebf4/vae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
@@ -20,7 +20,7 @@
20
  "layers_per_block": 2,
21
  "norm_num_groups": 32,
22
  "out_channels": 3,
23
- "sample_size": 512,
24
  "scaling_factor": 0.18215,
25
  "up_block_types": [
26
  "UpDecoderBlock2D",
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": "/home/sangkyung/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1-base/snapshots/dcd3ee64f0c1aba2eb9e0c0c16041c6cae40d780/vae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
 
20
  "layers_per_block": 2,
21
  "norm_num_groups": 32,
22
  "out_channels": 3,
23
+ "sample_size": 768,
24
  "scaling_factor": 0.18215,
25
  "up_block_types": [
26
  "UpDecoderBlock2D",
vae/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c02e0c7c263a4c0630ca3a72380ff55b9e38e0ab41d64dff7bf620a58342bc75
3
  size 334712113
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b01618945554d9840701d3453d4a9fe3db0db090164a5ed6305641306285b6f
3
  size 334712113