Hugging Face's logo

Aya168
/
instruct-pix2pix-model-20const

Diffusers
TensorBoard
Safetensors
StableDiffusionInstructPix2PixImagePipeline
Model card Files
xet
 Metrics Community
Aya168 commited on
Commit
41a7256
·
verified ·
1 Parent(s): 4febd27

End of training

Browse files
Files changed (18) 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 +1 -1
  9. logs/instruct-pix2pix/1732823426.5808117/events.out.tfevents.1732823426.plato2.232866.1 +3 -0
  10. logs/instruct-pix2pix/1732823426.588166/hparams.yml +51 -0
  11. logs/instruct-pix2pix/1732823661.8023863/events.out.tfevents.1732823661.plato2.233602.1 +3 -0
  12. logs/instruct-pix2pix/1732823661.8183439/hparams.yml +51 -0
  13. logs/instruct-pix2pix/1732823737.122964/events.out.tfevents.1732823737.plato2.234270.1 +3 -0
  14. logs/instruct-pix2pix/1732823737.2498505/hparams.yml +51 -0
  15. logs/instruct-pix2pix/events.out.tfevents.1732823426.plato2.232866.0 +3 -0
  16. logs/instruct-pix2pix/events.out.tfevents.1732823661.plato2.233602.0 +3 -0
  17. logs/instruct-pix2pix/events.out.tfevents.1732823736.plato2.234270.0 +3 -0
  18. unet/diffusion_pytorch_model.safetensors +1 -1
checkpoint-5000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00451a60a4791526cd530fb0d831b2cee70a722f16dc7966ab2b5da8df906f0a
3
+ size 2177645270
checkpoint-5000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37317385ed76d818c1381640cb9337a19b47c68559e8c800f628f2f3e1f0e53f
3
+ size 14864
checkpoint-5000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d96574c31739dec68d3aa37100e570cc1a02a6adeed9a67ccd6218eee0c89fa
3
+ size 1064
checkpoint-5000/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.30.0.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 sha256:39e74449d7fa94bfabe3d677c8c193631d77f115ed9f3714ecb7d63ac8ba3b38
3
+ size 3438213624
checkpoint-5000/unet_ema/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.30.0.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 sha256:55f3d4dc72ee04f0b4f8ddc8d84b31b4945e31e773c3b47c621695173dc3673f
3
+ size 3438213624
emb_opt.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c88371e789f1f93ccb9331ce7efb54ac62d798175c00712170433a81eb42f38
3
  size 19689394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60bb71786b25eb5d3882001384c99fc26bc6556e96edc94a7a0960fac2b3e2c8
3
  size 19689394
logs/instruct-pix2pix/1732823426.5808117/events.out.tfevents.1732823426.plato2.232866.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e060ab171743a1298df12f0686ab9906453c8fbe16172d897229f4bdcccb76b
3
+ size 2400
logs/instruct-pix2pix/1732823426.588166/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: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
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: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 1
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
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/1732823661.8023863/events.out.tfevents.1732823661.plato2.233602.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5caaa59b3e1cbfbac4133665eab70457c43144e3fae73a9d1b43e621f3e7c86c
3
+ size 2412
logs/instruct-pix2pix/1732823661.8183439/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: 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-20const
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/1732823737.122964/events.out.tfevents.1732823737.plato2.234270.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28fc60da00ac79ef98750399e4e6ae3908be20c4092a94e7f8b242275f84a2fb
3
+ size 2412
logs/instruct-pix2pix/1732823737.2498505/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: 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: 5000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 5
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
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/events.out.tfevents.1732823426.plato2.232866.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d92bdeb8f09e0a107a8fd79185cf63162df33e97978bff9e02e74f5314c020
3
+ size 136
logs/instruct-pix2pix/events.out.tfevents.1732823661.plato2.233602.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd39706814a72c288efd9ac1397bd31ae5276c404a16897f67a289dbb9297c91
3
+ size 184
logs/instruct-pix2pix/events.out.tfevents.1732823736.plato2.234270.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2d057dd2ba4feb93c007405cc8aa750a061b755e503c39bd5d65503c8147c63
3
+ size 244961
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d63362bd0df1627fa26411cf906b5640c97d958248d886943cb2062b511b747e
3
  size 3438213624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f3d4dc72ee04f0b4f8ddc8d84b31b4945e31e773c3b47c621695173dc3673f
3
  size 3438213624