Hugging Face's logo

nishant-glance
/
model-sd-2-1-priorp-unet-2000-lr2e-ab

Text-to-Image
Diffusers
TensorBoard
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
dreambooth
Inference Endpoints
Model card Files Metrics Community
nishant-glance commited on
Commit
b5ef9cf
•
1 Parent(s): 63ccf80

End of training

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +22 -0
  2. checkpoint-1000/optimizer.bin +3 -0
  3. checkpoint-1000/random_states_0.pkl +3 -0
  4. checkpoint-1000/scheduler.bin +3 -0
  5. checkpoint-1000/text_encoder/config.json +25 -0
  6. checkpoint-1000/text_encoder/pytorch_model.bin +3 -0
  7. checkpoint-1000/unet/config.json +71 -0
  8. checkpoint-1000/unet/diffusion_pytorch_model.safetensors +3 -0
  9. checkpoint-1500/optimizer.bin +3 -0
  10. checkpoint-1500/random_states_0.pkl +3 -0
  11. checkpoint-1500/scheduler.bin +3 -0
  12. checkpoint-1500/text_encoder/config.json +25 -0
  13. checkpoint-1500/text_encoder/pytorch_model.bin +3 -0
  14. checkpoint-1500/unet/config.json +71 -0
  15. checkpoint-1500/unet/diffusion_pytorch_model.safetensors +3 -0
  16. checkpoint-2000/optimizer.bin +3 -0
  17. checkpoint-2000/random_states_0.pkl +3 -0
  18. checkpoint-2000/scheduler.bin +3 -0
  19. checkpoint-2000/text_encoder/config.json +25 -0
  20. checkpoint-2000/text_encoder/pytorch_model.bin +3 -0
  21. checkpoint-2000/unet/config.json +71 -0
  22. checkpoint-2000/unet/diffusion_pytorch_model.safetensors +3 -0
  23. checkpoint-500/optimizer.bin +3 -0
  24. checkpoint-500/random_states_0.pkl +3 -0
  25. checkpoint-500/scheduler.bin +3 -0
  26. checkpoint-500/text_encoder/config.json +25 -0
  27. checkpoint-500/text_encoder/pytorch_model.bin +3 -0
  28. checkpoint-500/unet/config.json +71 -0
  29. checkpoint-500/unet/diffusion_pytorch_model.safetensors +3 -0
  30. feature_extractor/preprocessor_config.json +28 -0
  31. logs/dreambooth/1693313956.3751738/events.out.tfevents.1693313956.glancefeed-nishant-oli-gpu-replica.117864.1 +3 -0
  32. logs/dreambooth/1693313956.3769238/hparams.yml +58 -0
  33. logs/dreambooth/1693314085.1323035/events.out.tfevents.1693314085.glancefeed-nishant-oli-gpu-replica.119058.1 +3 -0
  34. logs/dreambooth/1693314085.1339548/hparams.yml +58 -0
  35. logs/dreambooth/1693314125.0590603/events.out.tfevents.1693314125.glancefeed-nishant-oli-gpu-replica.119193.1 +3 -0
  36. logs/dreambooth/1693314125.0612516/hparams.yml +58 -0
  37. logs/dreambooth/events.out.tfevents.1693313956.glancefeed-nishant-oli-gpu-replica.117864.0 +3 -0
  38. logs/dreambooth/events.out.tfevents.1693314085.glancefeed-nishant-oli-gpu-replica.119058.0 +3 -0
  39. logs/dreambooth/events.out.tfevents.1693314125.glancefeed-nishant-oli-gpu-replica.119193.0 +3 -0
  40. model_index.json +34 -0
  41. scheduler/scheduler_config.json +20 -0
  42. text_encoder/config.json +25 -0
  43. text_encoder/model.safetensors +3 -0
  44. tokenizer/merges.txt +0 -0
  45. tokenizer/special_tokens_map.json +24 -0
  46. tokenizer/tokenizer_config.json +33 -0
  47. tokenizer/vocab.json +0 -0
  48. unet/config.json +71 -0
  49. unet/diffusion_pytorch_model.safetensors +3 -0
  50. vae/config.json +32 -0
README.md ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: stabilityai/stable-diffusion-2-1
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-2-1-priorp-unet-2000-lr2e-ab
16
+
17
+ This is a dreambooth model derived from stabilityai/stable-diffusion-2-1. 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:f6bad56e4b14a30c8aba71c210dd592295eb27aab6a4fa471557fa0ded8f4ca3
3
+ size 9651298479
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:630ab0cff0586f079165abdc206a6b7fb75dc504092c2ab01d938c1180d5f1c8
3
+ size 15755
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": "stabilityai/stable-diffusion-2-1",
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": "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",
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 sha256:073c0aeac133b2fed019374d1b4fe3bef04b166e280a31e184235c5ab5ec5ce4
3
+ size 1361678941
checkpoint-1000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
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": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dual_cross_attention": false,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
+ "flip_sin_to_cos": true,
40
+ "freq_shift": 0,
41
+ "in_channels": 4,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "norm_eps": 1e-05,
47
+ "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "out_channels": 4,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_out_scale_factor": 1.0,
54
+ "resnet_skip_time_act": false,
55
+ "resnet_time_scale_shift": "default",
56
+ "sample_size": 96,
57
+ "time_cond_proj_dim": null,
58
+ "time_embedding_act_fn": null,
59
+ "time_embedding_dim": null,
60
+ "time_embedding_type": "positional",
61
+ "timestep_post_act": null,
62
+ "transformer_layers_per_block": 1,
63
+ "up_block_types": [
64
+ "UpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D"
68
+ ],
69
+ "upcast_attention": true,
70
+ "use_linear_projection": true
71
+ }
checkpoint-1000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94c1c8842a3551a2442050a4c8d7943c3b072c826001ca970b8a1cf81f592fe6
3
+ size 3463726504
checkpoint-1500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffdafd3ece00d3840868fd2bb64b7018dbc83f84657ad1c4bab0f78e78e5e3c6
3
+ size 9651298479
checkpoint-1500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:190f6a08775cc729c238041bf58a5c3d76032d11a93326e10b9e3160cc895012
3
+ size 15755
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": "stabilityai/stable-diffusion-2-1",
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": "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",
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:f388c44492dd687def53767ae48599c2cfbd48bf2847cd31878f21bf3ea574be
3
+ size 1361678941
checkpoint-1500/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
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": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dual_cross_attention": false,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
+ "flip_sin_to_cos": true,
40
+ "freq_shift": 0,
41
+ "in_channels": 4,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "norm_eps": 1e-05,
47
+ "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "out_channels": 4,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_out_scale_factor": 1.0,
54
+ "resnet_skip_time_act": false,
55
+ "resnet_time_scale_shift": "default",
56
+ "sample_size": 96,
57
+ "time_cond_proj_dim": null,
58
+ "time_embedding_act_fn": null,
59
+ "time_embedding_dim": null,
60
+ "time_embedding_type": "positional",
61
+ "timestep_post_act": null,
62
+ "transformer_layers_per_block": 1,
63
+ "up_block_types": [
64
+ "UpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D"
68
+ ],
69
+ "upcast_attention": true,
70
+ "use_linear_projection": true
71
+ }
checkpoint-1500/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b34df6636b51af36874870fae1ce04ef2b5e1132776b98680ca6b33241e0b8
3
+ size 3463726504
checkpoint-2000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0112015cf49df48f7142a34b4495cbac53a442ab779fc8dca0d108f1e0de82ee
3
+ size 9651298479
checkpoint-2000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd26749355a9a0c07e89a75353e0a86c9d36ff7ef920353fdd111d1bdf672072
3
+ size 15755
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": "stabilityai/stable-diffusion-2-1",
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": "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",
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 sha256:8f1787210ed66214b7fe183444a32eff24f133d8c4e63487631d2b83dd4ead55
3
+ size 1361678941
checkpoint-2000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
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": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dual_cross_attention": false,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
+ "flip_sin_to_cos": true,
40
+ "freq_shift": 0,
41
+ "in_channels": 4,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "norm_eps": 1e-05,
47
+ "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "out_channels": 4,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_out_scale_factor": 1.0,
54
+ "resnet_skip_time_act": false,
55
+ "resnet_time_scale_shift": "default",
56
+ "sample_size": 96,
57
+ "time_cond_proj_dim": null,
58
+ "time_embedding_act_fn": null,
59
+ "time_embedding_dim": null,
60
+ "time_embedding_type": "positional",
61
+ "timestep_post_act": null,
62
+ "transformer_layers_per_block": 1,
63
+ "up_block_types": [
64
+ "UpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D"
68
+ ],
69
+ "upcast_attention": true,
70
+ "use_linear_projection": true
71
+ }
checkpoint-2000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e701a1681e516cad12c85d500b4433a25d5734d8b306f913ff0e353a2350852
3
+ size 3463726504
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ecdbe7000bb0278ef5cd66f2dc7b5793f64e222f494f45b538bd95a651754ac
3
+ size 9651298479
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb392c9f47b704e2c0bebe57252361d3f854ad6d19f58d227abed0803f79843
3
+ size 15755
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": "stabilityai/stable-diffusion-2-1",
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": "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",
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:d89f3ce22b2431226a9001410bce5f367f271e31266bb2ef4ec31769742c78ee
3
+ size 1361678941
checkpoint-500/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
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": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dual_cross_attention": false,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
+ "flip_sin_to_cos": true,
40
+ "freq_shift": 0,
41
+ "in_channels": 4,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "norm_eps": 1e-05,
47
+ "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "out_channels": 4,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_out_scale_factor": 1.0,
54
+ "resnet_skip_time_act": false,
55
+ "resnet_time_scale_shift": "default",
56
+ "sample_size": 96,
57
+ "time_cond_proj_dim": null,
58
+ "time_embedding_act_fn": null,
59
+ "time_embedding_dim": null,
60
+ "time_embedding_type": "positional",
61
+ "timestep_post_act": null,
62
+ "transformer_layers_per_block": 1,
63
+ "up_block_types": [
64
+ "UpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D"
68
+ ],
69
+ "upcast_attention": true,
70
+ "use_linear_projection": true
71
+ }
checkpoint-500/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8222a845ac3e0b9c466ceeb9280c03551d816fc5a3534cd4758dc57aab3a1cbf
3
+ size 3463726504
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/1693313956.3751738/events.out.tfevents.1693313956.glancefeed-nishant-oli-gpu-replica.117864.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70c218b0823afb8cde1d5984841503d48273dc43c061df46157ff1dcaeee82e4
3
+ size 2909
logs/dreambooth/1693313956.3769238/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-2-1-priorp-unet-2000-lr2e-ab
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: ab2
19
+ instance_prompt: a photo of sks woman
20
+ learning_rate: 2.0e-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: 2400
29
+ mixed_precision: null
30
+ num_class_images: 200
31
+ num_train_epochs: 24
32
+ num_validation_images: 4
33
+ offset_noise: false
34
+ output_dir: model-sd-2-1-priorp-unet-2000-lr2e-ab
35
+ pre_compute_text_embeddings: false
36
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
37
+ prior_generation_precision: null
38
+ prior_loss_weight: 1.0
39
+ push_to_hub: true
40
+ report_to: tensorboard
41
+ resolution: 768
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ sample_batch_size: 4
45
+ scale_lr: false
46
+ seed: null
47
+ set_grads_to_none: false
48
+ skip_save_text_encoder: false
49
+ 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/1693314085.1323035/events.out.tfevents.1693314085.glancefeed-nishant-oli-gpu-replica.119058.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5949b9166f7a1a1b1b8a6e4fe82e3b1e049238620f1c6023d0efb91dfa8be9ce
3
+ size 2909
logs/dreambooth/1693314085.1339548/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-2-1-priorp-unet-2000-lr2e-ab
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: ab2
19
+ instance_prompt: a photo of sks woman
20
+ learning_rate: 2.0e-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: 2400
29
+ mixed_precision: null
30
+ num_class_images: 200
31
+ num_train_epochs: 24
32
+ num_validation_images: 4
33
+ offset_noise: false
34
+ output_dir: model-sd-2-1-priorp-unet-2000-lr2e-ab
35
+ pre_compute_text_embeddings: false
36
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
37
+ prior_generation_precision: null
38
+ prior_loss_weight: 1.0
39
+ push_to_hub: true
40
+ report_to: tensorboard
41
+ resolution: 768
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ sample_batch_size: 4
45
+ scale_lr: false
46
+ seed: null
47
+ set_grads_to_none: false
48
+ skip_save_text_encoder: false
49
+ 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/1693314125.0590603/events.out.tfevents.1693314125.glancefeed-nishant-oli-gpu-replica.119193.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe88192250fe85713615882e99abeb840b3cb5aa2275e820cb7fa9d85a618f8e
3
+ size 2909
logs/dreambooth/1693314125.0612516/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-2-1-priorp-unet-2000-lr2e-ab
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: ab2
19
+ instance_prompt: a photo of sks woman
20
+ learning_rate: 2.0e-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: 2400
29
+ mixed_precision: null
30
+ num_class_images: 200
31
+ num_train_epochs: 24
32
+ num_validation_images: 4
33
+ offset_noise: false
34
+ output_dir: model-sd-2-1-priorp-unet-2000-lr2e-ab
35
+ pre_compute_text_embeddings: false
36
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
37
+ prior_generation_precision: null
38
+ prior_loss_weight: 1.0
39
+ push_to_hub: true
40
+ report_to: tensorboard
41
+ resolution: 768
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ sample_batch_size: 4
45
+ scale_lr: false
46
+ seed: null
47
+ set_grads_to_none: false
48
+ skip_save_text_encoder: false
49
+ 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/events.out.tfevents.1693313956.glancefeed-nishant-oli-gpu-replica.117864.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d7cbb531c5cf2ea220f37ba647f7b2a0345cfe6565aef641adea447a574ae6
3
+ size 88
logs/dreambooth/events.out.tfevents.1693314085.glancefeed-nishant-oli-gpu-replica.119058.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3fe796d32e054f718c3e81f7aeb56117b080f592b2de57f958d3e4b3e772bf
3
+ size 252
logs/dreambooth/events.out.tfevents.1693314125.glancefeed-nishant-oli-gpu-replica.119193.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b55015a40404d42e608e6f9333390ef75e4d988942f03cb71045df305d094f4
3
+ size 201434
model_index.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "requires_safety_checker": false,
10
+ "safety_checker": [
11
+ null,
12
+ null
13
+ ],
14
+ "scheduler": [
15
+ "diffusers",
16
+ "DDIMScheduler"
17
+ ],
18
+ "text_encoder": [
19
+ "transformers",
20
+ "CLIPTextModel"
21
+ ],
22
+ "tokenizer": [
23
+ "transformers",
24
+ "CLIPTokenizer"
25
+ ],
26
+ "unet": [
27
+ "diffusers",
28
+ "UNet2DConditionModel"
29
+ ],
30
+ "vae": [
31
+ "diffusers",
32
+ "AutoencoderKL"
33
+ ]
34
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "v_prediction",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
+ "set_alpha_to_one": false,
15
+ "skip_prk_steps": true,
16
+ "steps_offset": 1,
17
+ "thresholding": false,
18
+ "timestep_spacing": "leading",
19
+ "trained_betas": null
20
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
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": "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",
23
+ "transformers_version": "4.32.0",
24
+ "vocab_size": 49408
25
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5086961a34871b313d9e4c642aca2fdf712160ddf80e34c14e415da5ae3db755
3
+ size 1361596304
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "!",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "do_lower_case": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 77,
23
+ "pad_token": "<|endoftext|>",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
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": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dual_cross_attention": false,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
+ "flip_sin_to_cos": true,
40
+ "freq_shift": 0,
41
+ "in_channels": 4,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "norm_eps": 1e-05,
47
+ "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "out_channels": 4,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_out_scale_factor": 1.0,
54
+ "resnet_skip_time_act": false,
55
+ "resnet_time_scale_shift": "default",
56
+ "sample_size": 96,
57
+ "time_cond_proj_dim": null,
58
+ "time_embedding_act_fn": null,
59
+ "time_embedding_dim": null,
60
+ "time_embedding_type": "positional",
61
+ "timestep_post_act": null,
62
+ "transformer_layers_per_block": 1,
63
+ "up_block_types": [
64
+ "UpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D"
68
+ ],
69
+ "upcast_attention": true,
70
+ "use_linear_projection": true
71
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d688864e6cc1eb82124c9b16fdf0eae06e86425bb31d9ae51fbb81c69e4d9a
3
+ size 3463726504
vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "/home/jupyter/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1/snapshots/5cae40e6a2745ae2b01ad92ae5043f95f23644d6/vae",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "force_upcast": true,
19
+ "in_channels": 3,
20
+ "latent_channels": 4,
21
+ "layers_per_block": 2,
22
+ "norm_num_groups": 32,
23
+ "out_channels": 3,
24
+ "sample_size": 768,
25
+ "scaling_factor": 0.18215,
26
+ "up_block_types": [
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D"
31
+ ]
32
+ }