Hugging Face's logo

ADT1999
/
instruct-pix2pix-model-trial

Diffusers
TensorBoard
Safetensors
StableDiffusionInstructPix2PixImagePipeline
Model card Files Metrics Community
ADT1999 commited on
Commit
961085d
·
verified ·
1 Parent(s): 2c7b5ad

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. checkpoint-5000/optimizer.bin +3 -0
  2. checkpoint-5000/random_states_0.pkl +3 -0
  3. checkpoint-5000/scheduler.bin +3 -0
  4. checkpoint-5000/unet/config.json +68 -0
  5. checkpoint-5000/unet/diffusion_pytorch_model.safetensors +3 -0
  6. checkpoint-5000/unet_ema/config.json +75 -0
  7. checkpoint-5000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  8. emb_opt.pt +3 -0
  9. feature_extractor/preprocessor_config.json +27 -0
  10. image_encoder/config.json +23 -0
  11. image_encoder/model.safetensors +3 -0
  12. logs/instruct-pix2pix/1732822103.994094/events.out.tfevents.1732822103.plato2.223750.1 +3 -0
  13. logs/instruct-pix2pix/1732822104.0003269/hparams.yml +51 -0
  14. logs/instruct-pix2pix/1732822498.7865715/events.out.tfevents.1732822498.plato2.226204.1 +3 -0
  15. logs/instruct-pix2pix/1732822498.7943935/hparams.yml +51 -0
  16. logs/instruct-pix2pix/1732823873.7111151/events.out.tfevents.1732823873.plato2.234876.1 +3 -0
  17. logs/instruct-pix2pix/1732823873.7524674/hparams.yml +51 -0
  18. logs/instruct-pix2pix/1732825875.0076709/events.out.tfevents.1732825875.plato2.239740.1 +3 -0
  19. logs/instruct-pix2pix/1732825875.0464149/hparams.yml +51 -0
  20. logs/instruct-pix2pix/1732825996.6006348/events.out.tfevents.1732825996.plato2.240014.1 +3 -0
  21. logs/instruct-pix2pix/1732825996.6074164/hparams.yml +51 -0
  22. logs/instruct-pix2pix/1732826890.7844646/events.out.tfevents.1732826890.plato2.241241.1 +3 -0
  23. logs/instruct-pix2pix/1732826890.7923768/hparams.yml +51 -0
  24. logs/instruct-pix2pix/1732827139.5223982/events.out.tfevents.1732827139.plato2.245921.1 +3 -0
  25. logs/instruct-pix2pix/1732827139.5288413/hparams.yml +51 -0
  26. logs/instruct-pix2pix/1733054300.2140543/events.out.tfevents.1733054300.plato2.515295.1 +3 -0
  27. logs/instruct-pix2pix/1733054300.2361934/hparams.yml +51 -0
  28. logs/instruct-pix2pix/1733054707.9502256/events.out.tfevents.1733054707.plato2.516537.1 +3 -0
  29. logs/instruct-pix2pix/1733054707.9575388/hparams.yml +51 -0
  30. logs/instruct-pix2pix/1733054982.2245855/events.out.tfevents.1733054982.plato2.517009.1 +3 -0
  31. logs/instruct-pix2pix/1733054982.239674/hparams.yml +51 -0
  32. logs/instruct-pix2pix/events.out.tfevents.1732822103.plato2.223750.0 +3 -0
  33. logs/instruct-pix2pix/events.out.tfevents.1732822498.plato2.226204.0 +3 -0
  34. logs/instruct-pix2pix/events.out.tfevents.1732823873.plato2.234876.0 +3 -0
  35. logs/instruct-pix2pix/events.out.tfevents.1732825874.plato2.239740.0 +3 -0
  36. logs/instruct-pix2pix/events.out.tfevents.1732825996.plato2.240014.0 +3 -0
  37. logs/instruct-pix2pix/events.out.tfevents.1732826890.plato2.241241.0 +3 -0
  38. logs/instruct-pix2pix/events.out.tfevents.1732827139.plato2.245921.0 +3 -0
  39. logs/instruct-pix2pix/events.out.tfevents.1733054300.plato2.515295.0 +3 -0
  40. logs/instruct-pix2pix/events.out.tfevents.1733054707.plato2.516537.0 +3 -0
  41. logs/instruct-pix2pix/events.out.tfevents.1733054982.plato2.517009.0 +3 -0
  42. model_index.json +38 -0
  43. scheduler/scheduler_config.json +16 -0
  44. text_encoder/config.json +25 -0
  45. text_encoder/model.safetensors +3 -0
  46. tokenizer/merges.txt +0 -0
  47. tokenizer/special_tokens_map.json +30 -0
  48. tokenizer/tokenizer_config.json +30 -0
  49. tokenizer/vocab.json +0 -0
  50. unet/config.json +68 -0
checkpoint-5000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:823225fa50199434b3afd4e816fa61d962ac7067223d172c961135dcaf477a5e
3
+ size 44107828
checkpoint-5000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde8b8eb4e130ed30ff207d69d603591fa0b3637c26c9f93682306bfa7fc405e
3
+ size 14864
checkpoint-5000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8a348e436b7c6bc26fe51ee1b7a68bf53c5fc70b67dded75b5e22ff687ed0ea
3
+ size 1064
checkpoint-5000/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0.dev0",
4
+ "_name_or_path": "paint-by-inpaint/add-base",
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-5000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6776fbc43cd4770af12656abffcb409418843e14d04ec7b231cb8d4ea5eb11e9
3
+ size 3438213624
checkpoint-5000/unet_ema/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0.dev0",
4
+ "_name_or_path": "paint-by-inpaint/add-base",
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": 5000,
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-5000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6776fbc43cd4770af12656abffcb409418843e14d04ec7b231cb8d4ea5eb11e9
3
+ size 3438213624
emb_opt.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed361e2a925047b163c51c7254dba5aa61707849310761a9a9f033301f9b48bb
3
+ size 22052332
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
image_encoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-large-patch14",
3
+ "architectures": [
4
+ "CLIPVisionModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "quick_gelu",
9
+ "hidden_size": 1024,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 24,
19
+ "patch_size": 14,
20
+ "projection_dim": 768,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.44.2"
23
+ }
image_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b33d2a3a643650857672e880ccf73adbaf114fbbadec36d142ee9d48af7e20
3
+ size 1215912728
logs/instruct-pix2pix/1732822103.994094/events.out.tfevents.1732822103.plato2.223750.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f295782fc4864d5ae5d08402f5cf975a47bc5736ab5ab40266d6a28c6cc04e2
3
+ size 2401
logs/instruct-pix2pix/1732822104.0003269/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ADT1999/project_from_PIPE-bug
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: cosine
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 8000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 15
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-trial
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 16
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732822498.7865715/events.out.tfevents.1732822498.plato2.226204.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b5b746300d3969c414a178c686ba1fb8538d00f4c8d433071daaae524e1722
3
+ size 2401
logs/instruct-pix2pix/1732822498.7943935/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ADT1999/project_from_PIPE-bug
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: cosine
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 8000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 15
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-trial
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 16
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732823873.7111151/events.out.tfevents.1732823873.plato2.234876.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8cd43101cbed740cfd970f8ca30506865d80e4ff443d0e727c064ccc04a3e57
3
+ size 2405
logs/instruct-pix2pix/1732823873.7524674/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ADT1999/project_from_PIPE-bug
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: polynomial
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 20000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 18
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-trial
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732825875.0076709/events.out.tfevents.1732825875.plato2.239740.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e794eaeddf558bdf8996c6f0b860239154f3451e70566d08e5a77747a57807
3
+ size 2405
logs/instruct-pix2pix/1732825875.0464149/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ADT1999/project_from_PIPE-bug
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 0.0001
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: polynomial
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 20000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 18
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-trial
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732825996.6006348/events.out.tfevents.1732825996.plato2.240014.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:286bf91e57b78354be66983dc7c7d58c949836e70ae2a1013324d4e685007e8d
3
+ size 2405
logs/instruct-pix2pix/1732825996.6074164/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ADT1999/project_from_PIPE-bug
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 0.0001
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: polynomial
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 14000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 13
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-trial
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732826890.7844646/events.out.tfevents.1732826890.plato2.241241.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aea091a22248caa22dc8c2d675ad37b988427c502d34fed6bee6d177022e2c1d
3
+ size 2410
logs/instruct-pix2pix/1732826890.7923768/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ADT1999/project_from_PIPE_extended
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 0.0001
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: polynomial
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 15000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 14
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-trial
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732827139.5223982/events.out.tfevents.1732827139.plato2.245921.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3063b637772c70dedc12d0ac8a0ab2a14859d1f8a0e8476e40b5dcd9e12503ea
3
+ size 2410
logs/instruct-pix2pix/1732827139.5288413/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ADT1999/project_from_PIPE_extended
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 0.0001
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: polynomial
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 15000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 14
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-trial
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1733054300.2140543/events.out.tfevents.1733054300.plato2.515295.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20ec5391cbd45726811aa18aaa860d705370bed88cd080cf9a0f82fcf0488379
3
+ size 2410
logs/instruct-pix2pix/1733054300.2361934/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ADT1999/project_from_PIPE_extended
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 0.0001
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: polynomial
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 15000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 14
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-trial
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1733054707.9502256/events.out.tfevents.1733054707.plato2.516537.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80ebc45fb69aeb77543bd2419d6b310b178f9fa7a4063ab598f20c7ec15c1a8d
3
+ size 2410
logs/instruct-pix2pix/1733054707.9575388/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ADT1999/project_from_PIPE_extended
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 0.0001
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: polynomial
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 5000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 3
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-trial
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
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
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1733054982.2245855/events.out.tfevents.1733054982.plato2.517009.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b70f2268cfdeef6951e35dd8b77e3a0cc04027bcbb0be0f73102c6c0f9b03ffc
3
+ size 2410
logs/instruct-pix2pix/1733054982.239674/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ADT1999/project_from_PIPE_extended
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 0.0001
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: polynomial
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 5000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 3
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-trial
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
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
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/events.out.tfevents.1732822103.plato2.223750.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2609fa6188c2ee44cc2c65c925eb02f474b21760c9ed84a8ce8a5991d762ce
3
+ size 280
logs/instruct-pix2pix/events.out.tfevents.1732822498.plato2.226204.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd5bd6f37dce7ef92477983f7dd6c0f73bf4b182f560a462ecf193315371863
3
+ size 664
logs/instruct-pix2pix/events.out.tfevents.1732823873.plato2.234876.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0991bf731ed1357e673d673698cff12805966d95d1770c8094f1be799bebea09
3
+ size 184
logs/instruct-pix2pix/events.out.tfevents.1732825874.plato2.239740.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9088b40c66c1b90508513053616ebb83761eb9a2f6dac72201a09836ecc7bc53
3
+ size 280
logs/instruct-pix2pix/events.out.tfevents.1732825996.plato2.240014.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b29b6835f81f346462fce8561acc450f2ed21de0b5d284703f1d39fb114257
3
+ size 280
logs/instruct-pix2pix/events.out.tfevents.1732826890.plato2.241241.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ca2175b06c32f7570f059bc482c2575f956b8429aef6e1be39c35af6b77f0c0
3
+ size 280
logs/instruct-pix2pix/events.out.tfevents.1732827139.plato2.245921.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19b3dd94c791d2c33579546cb08b04e0c5b62a52b838d02dc0eb54910818e182
3
+ size 299204
logs/instruct-pix2pix/events.out.tfevents.1733054300.plato2.515295.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf8000318509bf1cc317a5dbdadf6ff91640af9130375ab8c6c482d167afeaa
3
+ size 280
logs/instruct-pix2pix/events.out.tfevents.1733054707.plato2.516537.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a8d6d274fc17d5f5fb3ae3258a4544fe5e5781fa8439967d14d0eba7e3a435
3
+ size 1720
logs/instruct-pix2pix/events.out.tfevents.1733054982.plato2.517009.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f48fa7ad0ffdf62bef04be51761c101c5f87188a571e9a38f950623b9775a88
3
+ size 244961
model_index.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionInstructPix2PixImagePipeline",
3
+ "_diffusers_version": "0.31.0.dev0",
4
+ "_name_or_path": "paint-by-inpaint/add-base",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "image_encoder": [
10
+ "transformers",
11
+ "CLIPVisionModelWithProjection"
12
+ ],
13
+ "requires_safety_checker": true,
14
+ "safety_checker": [
15
+ null,
16
+ null
17
+ ],
18
+ "scheduler": [
19
+ "diffusers",
20
+ "EulerAncestralDiscreteScheduler"
21
+ ],
22
+ "text_encoder": [
23
+ "transformers",
24
+ "CLIPTextModel"
25
+ ],
26
+ "tokenizer": [
27
+ "transformers",
28
+ "CLIPTokenizer"
29
+ ],
30
+ "unet": [
31
+ "diffusers",
32
+ "UNet2DConditionModel"
33
+ ],
34
+ "vae": [
35
+ "diffusers",
36
+ "AutoencoderKL"
37
+ ]
38
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "EulerAncestralDiscreteScheduler",
3
+ "_diffusers_version": "0.31.0.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
+ "rescale_betas_zero_snr": false,
11
+ "set_alpha_to_one": false,
12
+ "skip_prk_steps": true,
13
+ "steps_offset": 1,
14
+ "timestep_spacing": "leading",
15
+ "trained_betas": null
16
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/adi.tsach/.cache/huggingface/hub/models--paint-by-inpaint--add-base/snapshots/79753a54092b836c77292b592f5c8c2e884728ef/text_encoder",
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": "float32",
23
+ "transformers_version": "4.44.2",
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 sha256:5c3d6454dd2d23414b56aa1b5858a72487a656937847b6fea8d0606d7a42cdbc
3
+ size 492265168
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|startoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "model_max_length": 77,
27
+ "pad_token": "<|endoftext|>",
28
+ "tokenizer_class": "CLIPTokenizer",
29
+ "unk_token": "<|endoftext|>"
30
+ }
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": "0.31.0.dev0",
4
+ "_name_or_path": "paint-by-inpaint/add-base",
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
+ }