Hugging Face's logo

StivenLancheros
/
instruct-pix2pix-random-christmas-edits

Diffusers
TensorBoard
Safetensors
StableDiffusionInstructPix2PixPipeline
Model card Files Metrics Community
StivenLancheros commited on
Commit
de61706
·
1 Parent(s): a04809b

End of training

Browse files
Files changed (35) hide show
  1. checkpoint-25000/optimizer.bin +3 -0
  2. checkpoint-25000/random_states_0.pkl +3 -0
  3. checkpoint-25000/scaler.pt +3 -0
  4. checkpoint-25000/scheduler.bin +3 -0
  5. checkpoint-25000/unet/config.json +68 -0
  6. checkpoint-25000/unet/diffusion_pytorch_model.safetensors +3 -0
  7. checkpoint-25000/unet_ema/config.json +75 -0
  8. checkpoint-25000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  9. feature_extractor/preprocessor_config.json +28 -0
  10. logs/instruct-pix2pix/1697802948.1595988/events.out.tfevents.1697802948.ironman.37690.1 +3 -0
  11. logs/instruct-pix2pix/1697802948.1623101/hparams.yml +50 -0
  12. logs/instruct-pix2pix/1698063879.0154102/events.out.tfevents.1698063879.ironman.16454.1 +3 -0
  13. logs/instruct-pix2pix/1698063879.0182116/hparams.yml +50 -0
  14. logs/instruct-pix2pix/1698160499.1665728/events.out.tfevents.1698160499.ironman.35175.1 +3 -0
  15. logs/instruct-pix2pix/1698160499.1692312/hparams.yml +50 -0
  16. logs/instruct-pix2pix/1698161401.9120111/events.out.tfevents.1698161401.ironman.35562.1 +3 -0
  17. logs/instruct-pix2pix/1698161401.9149716/hparams.yml +50 -0
  18. logs/instruct-pix2pix/events.out.tfevents.1697802948.ironman.37690.0 +3 -0
  19. logs/instruct-pix2pix/events.out.tfevents.1698063879.ironman.16454.0 +3 -0
  20. logs/instruct-pix2pix/events.out.tfevents.1698160499.ironman.35175.0 +3 -0
  21. logs/instruct-pix2pix/events.out.tfevents.1698161401.ironman.35562.0 +3 -0
  22. model_index.json +34 -0
  23. safety_checker/config.json +28 -0
  24. safety_checker/model.safetensors +3 -0
  25. scheduler/scheduler_config.json +15 -0
  26. text_encoder/config.json +25 -0
  27. text_encoder/model.safetensors +3 -0
  28. tokenizer/merges.txt +0 -0
  29. tokenizer/special_tokens_map.json +24 -0
  30. tokenizer/tokenizer_config.json +33 -0
  31. tokenizer/vocab.json +0 -0
  32. unet/config.json +68 -0
  33. unet/diffusion_pytorch_model.safetensors +3 -0
  34. vae/config.json +32 -0
  35. vae/diffusion_pytorch_model.safetensors +3 -0
checkpoint-25000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4b0ab2ccef481f711bbc1eb8867b0a91d0621b843401e1e72b76eff7eae40f
3
+ size 6876842324
checkpoint-25000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01a1f0b2510fcd4c07f60aaf9496488e8d0215ae16928a6ad1e8748f1d53463e
3
+ size 14864
checkpoint-25000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91758bb3bc55ffbf161afb386dcdf9604c395370dd46824bc6a25cc70ca6ee26
3
+ size 988
checkpoint-25000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea47d54490cec5ad7924c37c794fdc3f9ea5bad383ae45ba5c08daf4f244f7e
3
+ size 1000
checkpoint-25000/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stablediffusionapi/realistic-vision-v51",
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
+ "dropout": 0.0,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 8,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
40
+ "mid_block_scale_factor": 1,
41
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_attention_heads": null,
45
+ "num_class_embeds": null,
46
+ "only_cross_attention": false,
47
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "reverse_transformer_layers_per_block": null,
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "transformer_layers_per_block": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
checkpoint-25000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba3e393c53f2efa1d360b6762b873ae6122969c7febdf4096e8bef5a302b4d5
3
+ size 3438213624
checkpoint-25000/unet_ema/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stablediffusionapi/realistic-vision-v51",
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
+ "decay": 0.9999,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "dropout": 0.0,
33
+ "dual_cross_attention": false,
34
+ "encoder_hid_dim": null,
35
+ "encoder_hid_dim_type": null,
36
+ "flip_sin_to_cos": true,
37
+ "freq_shift": 0,
38
+ "in_channels": 8,
39
+ "inv_gamma": 1.0,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "min_decay": 0.0,
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
+ "optimization_step": 25000,
51
+ "out_channels": 4,
52
+ "power": 0.6666666666666666,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "update_after_step": 0,
73
+ "use_ema_warmup": false,
74
+ "use_linear_projection": false
75
+ }
checkpoint-25000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c3712044d2458a0518d2359ca29e20d83ee36f750bf8381bd0b865992446124
3
+ size 3438213624
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": "CLIPFeatureExtractor",
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/instruct-pix2pix/1697802948.1595988/events.out.tfevents.1697802948.ironman.37690.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78de70444d32494155acf4aa2922347f31cda27a0c580982798576a87b64c5dd
3
+ size 2429
logs/instruct-pix2pix/1697802948.1623101/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: fusing/instructpix2pix-1000-samples
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 5.0e-05
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 15000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 715
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: instruct-pix2pix-model
35
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
36
+ push_to_hub: false
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 256
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: false
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
logs/instruct-pix2pix/1698063879.0154102/events.out.tfevents.1698063879.ironman.16454.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb615be986174766b017bbd9503db14dcfcbbeabc946d78a5a2a38945a88ad98
3
+ size 2434
logs/instruct-pix2pix/1698063879.0182116/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: StivenLancheros/christmas-edits_dataset2
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 5.0e-05
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 15000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 9
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: instruct-pix2pix-model
35
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
logs/instruct-pix2pix/1698160499.1665728/events.out.tfevents.1698160499.ironman.35175.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681b2c7aaa7bbb92bb46f596aac9e3c2a203dffa12c2dd7d620c0bc0b87c706f
3
+ size 2443
logs/instruct-pix2pix/1698160499.1692312/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: StivenLancheros/christmas-edits_dataset2
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 5.0e-05
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 15000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 9
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: instruct-pix2pix-model
35
+ pretrained_model_name_or_path: stablediffusionapi/realistic-vision-v51
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
logs/instruct-pix2pix/1698161401.9120111/events.out.tfevents.1698161401.ironman.35562.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e5fc8976f8d67d884dabc7d1e917485c91eeaeac051de2595d365701b6d84c4
3
+ size 2443
logs/instruct-pix2pix/1698161401.9149716/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: StivenLancheros/christmas-edits_dataset2
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 5.0e-05
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 25000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 15
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: instruct-pix2pix-model
35
+ pretrained_model_name_or_path: stablediffusionapi/realistic-vision-v51
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
logs/instruct-pix2pix/events.out.tfevents.1697802948.ironman.37690.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:319ba39824a9a4146c1af958f1492921867aebc786e93b536fdd9191860f5bf2
3
+ size 2248
logs/instruct-pix2pix/events.out.tfevents.1698063879.ironman.16454.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e22c863cd37de927e3de4e280b295357dd01546fce68df2c792531e3aa6ea8a
3
+ size 734961
logs/instruct-pix2pix/events.out.tfevents.1698160499.ironman.35175.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9534e4ff44979e43fa5636782e3e12c328dc0be941424fa1addbfab15df228ec
3
+ size 7507
logs/instruct-pix2pix/events.out.tfevents.1698161401.ironman.35562.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7070aa0ff8939a01e92995831e05d2af180ee817daad155477beca945056058
3
+ size 1233578
model_index.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionInstructPix2PixPipeline",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stablediffusionapi/realistic-vision-v51",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPFeatureExtractor"
8
+ ],
9
+ "requires_safety_checker": true,
10
+ "safety_checker": [
11
+ "stable_diffusion",
12
+ "StableDiffusionSafetyChecker"
13
+ ],
14
+ "scheduler": [
15
+ "diffusers",
16
+ "PNDMScheduler"
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
+ }
safety_checker/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/mandsim/.cache/huggingface/hub/models--stablediffusionapi--realistic-vision-v51/snapshots/f9fcfadcf76895ecd8b254fd4e3d86b86d77338f/safety_checker",
3
+ "architectures": [
4
+ "StableDiffusionSafetyChecker"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "dropout": 0.0,
12
+ "hidden_size": 768,
13
+ "intermediate_size": 3072,
14
+ "model_type": "clip_text_model",
15
+ "num_attention_heads": 12
16
+ },
17
+ "torch_dtype": "float32",
18
+ "transformers_version": "4.32.1",
19
+ "vision_config": {
20
+ "dropout": 0.0,
21
+ "hidden_size": 1024,
22
+ "intermediate_size": 4096,
23
+ "model_type": "clip_vision_model",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "patch_size": 14
27
+ }
28
+ }
safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8836d43318e69143abd62046c3168db3556884e3f8057b0143c7ffe33408f586
3
+ size 1215979664
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "epsilon",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "timestep_spacing": "leading",
14
+ "trained_betas": null
15
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stablediffusionapi/realistic-vision-v51",
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": 768,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.32.1",
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 sha256:9706025d0e3053a3cdcc7e6cfa495c5ad951267a29ad08644aadb684ae217e7e
3
+ size 246144152
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": "<|endoftext|>",
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 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stablediffusionapi/realistic-vision-v51",
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
+ "dropout": 0.0,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 8,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
40
+ "mid_block_scale_factor": 1,
41
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_attention_heads": null,
45
+ "num_class_embeds": null,
46
+ "only_cross_attention": false,
47
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "reverse_transformer_layers_per_block": null,
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "transformer_layers_per_block": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c3712044d2458a0518d2359ca29e20d83ee36f750bf8381bd0b865992446124
3
+ size 3438213624
vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "stablediffusionapi/realistic-vision-v51",
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": 512,
25
+ "scaling_factor": 0.18215,
26
+ "up_block_types": [
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D"
31
+ ]
32
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
3
+ size 167335342