oljike commited on
Commit
19ddb2f
·
1 Parent(s): 5b54899

End of training

Browse files
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 jacksondavis man
6
+ tags:
7
+ - stable-diffusion
8
+ - stable-diffusion-diffusers
9
+ - text-to-image
10
+ - diffusers
11
+ - dreambooth
12
+ inference: true
13
+ ---
14
+
15
+ # DreamBooth - oljike/jackson_model
16
+
17
+ This is a dreambooth model derived from stabilityai/stable-diffusion-2-1. The weights were trained on a photo of jacksondavis man 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: False.
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3e42b668dcb5e5cf3a0b6da6c836ac88a357c9bd2e6bc8c4cdde7503a4f86fd
3
+ size 1737914501
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:430890cc3ed4de07da41bcd49efec046ca9c8912cdadbd22a9ed27203c55b2b3
3
+ size 14727
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f196a54202bb4ba1220e8c59f42f9cda0702d68ea83147d814c2fb2f36b8f2
3
+ size 557
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6be622d51c3bcf8a1991c02b9778f31d7e3a79a8b22e03e81a36e25205ef4c5b
3
+ size 563
checkpoint-500/unet/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.20.0.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
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280,
19
+ 1280
20
+ ],
21
+ "center_input_sample": false,
22
+ "class_embed_type": null,
23
+ "class_embeddings_concat": false,
24
+ "conv_in_kernel": 3,
25
+ "conv_out_kernel": 3,
26
+ "cross_attention_dim": 1024,
27
+ "cross_attention_norm": null,
28
+ "down_block_types": [
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "DownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 4,
41
+ "layers_per_block": 2,
42
+ "mid_block_only_cross_attention": null,
43
+ "mid_block_scale_factor": 1,
44
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "out_channels": 4,
51
+ "projection_class_embeddings_input_dim": null,
52
+ "resnet_out_scale_factor": 1.0,
53
+ "resnet_skip_time_act": false,
54
+ "resnet_time_scale_shift": "default",
55
+ "sample_size": 96,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": 1,
62
+ "up_block_types": [
63
+ "UpBlock2D",
64
+ "CrossAttnUpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D"
67
+ ],
68
+ "upcast_attention": true,
69
+ "use_linear_projection": true
70
+ }
checkpoint-500/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f5df64dc2e1284b91db190e4bd92f798d797b96255b612b1372fb3bf58238f4
3
+ size 3463934693
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/1693815500.2632525/events.out.tfevents.1693815500.ip-172-31-5-197.46940.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f84e5bb3ef634e1a9371fb953308d951efd98eeea74dfb807ea7c9f88d5248
3
+ size 2787
logs/dreambooth/1693815500.2657928/hparams.yml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: null
10
+ class_labels_conditioning: null
11
+ class_prompt: a photo of man
12
+ dataloader_num_workers: 0
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 2
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ instance_data_dir: ../../../data/people/Jackson-Davis Trayce/train
19
+ instance_prompt: a photo of jacksondavis man
20
+ learning_rate: 5.0e-06
21
+ local_rank: -1
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: 800
29
+ mixed_precision: null
30
+ num_class_images: 200
31
+ num_train_epochs: 73
32
+ num_validation_images: 4
33
+ offset_noise: false
34
+ output_dir: ../../models/jackson_model
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: 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: false
54
+ use_8bit_adam: true
55
+ validation_prompt: null
56
+ validation_steps: 100
57
+ with_prior_preservation: false
logs/dreambooth/1693815628.247069/events.out.tfevents.1693815628.ip-172-31-5-197.47006.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2d292dffb657d75171b698a3d8400f90a57101b70cdb8fdb8c5915e28392b0
3
+ size 2790
logs/dreambooth/1693815628.2485251/hparams.yml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: null
10
+ class_labels_conditioning: null
11
+ class_prompt: a photo of man
12
+ dataloader_num_workers: 0
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 2
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ instance_data_dir: ../../../data/people/Jackson-Davis Trayce/train_db
19
+ instance_prompt: a photo of jacksondavis man
20
+ learning_rate: 5.0e-06
21
+ local_rank: -1
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: 800
29
+ mixed_precision: null
30
+ num_class_images: 200
31
+ num_train_epochs: 73
32
+ num_validation_images: 4
33
+ offset_noise: false
34
+ output_dir: ../../models/jackson_model
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: 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: false
54
+ use_8bit_adam: true
55
+ validation_prompt: null
56
+ validation_steps: 100
57
+ with_prior_preservation: false
logs/dreambooth/1693815733.2253957/events.out.tfevents.1693815733.ip-172-31-5-197.47039.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb0233565012fc2eb102ec6457052712bac056f827efa39a24c392c25b1d333
3
+ size 2790
logs/dreambooth/1693815733.226867/hparams.yml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: null
10
+ class_labels_conditioning: null
11
+ class_prompt: a photo of man
12
+ dataloader_num_workers: 0
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 2
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ instance_data_dir: ../../../data/people/Jackson-Davis Trayce/train_db
19
+ instance_prompt: a photo of jacksondavis man
20
+ learning_rate: 5.0e-06
21
+ local_rank: -1
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: 800
29
+ mixed_precision: null
30
+ num_class_images: 200
31
+ num_train_epochs: 80
32
+ num_validation_images: 4
33
+ offset_noise: false
34
+ output_dir: ../../models/jackson_model
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: 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: false
54
+ use_8bit_adam: true
55
+ validation_prompt: null
56
+ validation_steps: 100
57
+ with_prior_preservation: false
logs/dreambooth/events.out.tfevents.1693815500.ip-172-31-5-197.46940.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29f4672653c41b4f9aafc03ac3eceab3624a3a42be8c74a8b1007e73472a8ea
3
+ size 1478
logs/dreambooth/events.out.tfevents.1693815628.ip-172-31-5-197.47006.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147002ed15cce12de0fcba3908880d60a34a2c43abb3e04245c61ba277421f0a
3
+ size 494
logs/dreambooth/events.out.tfevents.1693815733.ip-172-31-5-197.47039.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7179fdb871452515b8db44c451e2a6fcf35344ca5c13f00a889ae0c6054539a6
3
+ size 133974
model_index.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.20.0.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": "0.20.0.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": "float16",
23
+ "transformers_version": "4.26.1",
24
+ "vocab_size": 49408
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a06cf32cf585d03b55fef302142a5321b761ec440113925f64f4ceaffc7730
3
+ size 680904225
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "do_lower_case": true,
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 77,
22
+ "name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1/snapshots/5cae40e6a2745ae2b01ad92ae5043f95f23644d6/tokenizer",
23
+ "pad_token": "<|endoftext|>",
24
+ "special_tokens_map_file": "./special_tokens_map.json",
25
+ "tokenizer_class": "CLIPTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.20.0.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
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280,
19
+ 1280
20
+ ],
21
+ "center_input_sample": false,
22
+ "class_embed_type": null,
23
+ "class_embeddings_concat": false,
24
+ "conv_in_kernel": 3,
25
+ "conv_out_kernel": 3,
26
+ "cross_attention_dim": 1024,
27
+ "cross_attention_norm": null,
28
+ "down_block_types": [
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "DownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 4,
41
+ "layers_per_block": 2,
42
+ "mid_block_only_cross_attention": null,
43
+ "mid_block_scale_factor": 1,
44
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "out_channels": 4,
51
+ "projection_class_embeddings_input_dim": null,
52
+ "resnet_out_scale_factor": 1.0,
53
+ "resnet_skip_time_act": false,
54
+ "resnet_time_scale_shift": "default",
55
+ "sample_size": 96,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": 1,
62
+ "up_block_types": [
63
+ "UpBlock2D",
64
+ "CrossAttnUpBlock2D",
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D"
67
+ ],
68
+ "upcast_attention": true,
69
+ "use_linear_projection": true
70
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e46b3417d288960f516dea2b652da80d9a03fc017afb47b3b851b55689b1430
3
+ size 3463934693
vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.20.0.dev0",
4
+ "_name_or_path": "/home/ubuntu/.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
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b01618945554d9840701d3453d4a9fe3db0db090164a5ed6305641306285b6f
3
+ size 334712113