Hugging Face's logo

hhd23
/
instruct-pix2pix-model

Diffusers
TensorBoard
Safetensors
StableDiffusionInstructPix2PixPipeline
Model card Files Metrics Community
hhd23 commited on
Commit
9055ff8
•
1 Parent(s): 1d54cde

End of training

Browse files
Files changed (20) hide show
  1. checkpoint-40000/optimizer.bin +3 -0
  2. checkpoint-40000/random_states_0.pkl +3 -0
  3. checkpoint-40000/scaler.pt +3 -0
  4. checkpoint-40000/scheduler.bin +3 -0
  5. checkpoint-40000/unet/config.json +68 -0
  6. checkpoint-40000/unet/diffusion_pytorch_model.safetensors +3 -0
  7. logs/instruct-pix2pix/1713969713.1971943/events.out.tfevents.1713969713.ss4029d.11152.1 +3 -0
  8. logs/instruct-pix2pix/1713969713.20029/hparams.yml +51 -0
  9. logs/instruct-pix2pix/1714049651.3087144/events.out.tfevents.1714049651.ss4029d.3379.1 +3 -0
  10. logs/instruct-pix2pix/1714049651.312215/hparams.yml +51 -0
  11. logs/instruct-pix2pix/1714049698.7163846/events.out.tfevents.1714049698.ss4029d.7369.1 +3 -0
  12. logs/instruct-pix2pix/1714049698.7184625/hparams.yml +51 -0
  13. logs/instruct-pix2pix/1714049766.8812604/events.out.tfevents.1714049766.ss4029d.12156.1 +3 -0
  14. logs/instruct-pix2pix/1714049766.8830693/hparams.yml +51 -0
  15. logs/instruct-pix2pix/events.out.tfevents.1713969713.ss4029d.11152.0 +3 -0
  16. logs/instruct-pix2pix/events.out.tfevents.1714049651.ss4029d.3379.0 +3 -0
  17. logs/instruct-pix2pix/events.out.tfevents.1714049698.ss4029d.7369.0 +3 -0
  18. logs/instruct-pix2pix/events.out.tfevents.1714049766.ss4029d.12156.0 +3 -0
  19. unet/config.json +1 -1
  20. unet/diffusion_pytorch_model.safetensors +1 -1
checkpoint-40000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:506ee22feb4de7c6d6552b32fc43808da533f5649aafd2aa816558637cabfc78
3
+ size 6876851924
checkpoint-40000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91387fd3b90f4bebf33a3a481056ab144d9f07e207a5c91684ef1a64723659b9
3
+ size 15580
checkpoint-40000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ecdfd3ecfe57d31a640c6c49874abdf739cfeccb0d16184120bcefaca76bb6
3
+ size 988
checkpoint-40000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef798b977dd87493298e347d999e05aea036ff4f9988c06db5410cdf8c276567
3
+ size 1000
checkpoint-40000/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.28.0.dev0",
4
+ "_name_or_path": "instruct-pix2pix-model/checkpoint-20000",
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-40000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385fd71c886c06fcfc261221cb30c5efd429148ecc3594f6c1a3f7f6407b4a20
3
+ size 3438213624
logs/instruct-pix2pix/1713969713.1971943/events.out.tfevents.1713969713.ss4029d.11152.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a2f290583c25d596bb4ace52318c33d931665f15556fa04cccc94ebae22b62
3
+ size 2429
logs/instruct-pix2pix/1713969713.20029/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: 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: 40000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 77
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: 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
51
+ variant: null
logs/instruct-pix2pix/1714049651.3087144/events.out.tfevents.1714049651.ss4029d.3379.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a1a48ea9914686312776674d0ffde500f5be48018c638545bf28385febcc12a
3
+ size 2567
logs/instruct-pix2pix/1714049651.312215/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: 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: 40000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 77
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: 256
40
+ resume_from_checkpoint: /home/tang_21/Project/diffusers/examples/instruct_pix2pix/instruct-pix2pix-model
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
51
+ variant: null
logs/instruct-pix2pix/1714049698.7163846/events.out.tfevents.1714049698.ss4029d.7369.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d718db4a8be02510558315d614a719a8c439e7664d77ec6a144c85d7f366a417
3
+ size 2584
logs/instruct-pix2pix/1714049698.7184625/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: 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: 40000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 77
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: 256
40
+ resume_from_checkpoint: /home/tang_21/Project/diffusers/examples/instruct_pix2pix/instruct-pix2pix-model/checkpoint-20000
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
51
+ variant: null
logs/instruct-pix2pix/1714049766.8812604/events.out.tfevents.1714049766.ss4029d.12156.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1562315ab8575b840314c443b8379f252f0b38e2d16a8c4c2e2fa80077288d93
3
+ size 2584
logs/instruct-pix2pix/1714049766.8830693/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: 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: 40000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 77
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: 256
40
+ resume_from_checkpoint: /home/tang_21/Project/diffusers/examples/instruct_pix2pix/instruct-pix2pix-model/checkpoint-20000
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
51
+ variant: null
logs/instruct-pix2pix/events.out.tfevents.1713969713.ss4029d.11152.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d69da696403ca07a36d921069ff22612d0f4f1815a173391ba6f66125ee402a3
3
+ size 1032192
logs/instruct-pix2pix/events.out.tfevents.1714049651.ss4029d.3379.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cff94b6843d41ab1fdf84a1c13f326e55d186fbe992590f0fd9f14cf546d9ee
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1714049698.ss4029d.7369.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b80802f1daba50f3edbb8f652d984a07e3898632584ab6d89137987e39fead0
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1714049766.ss4029d.12156.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:114f25365abe237ed86447073939fb86cd66dda4b5fe746568d0f0f7dfd10ccb
3
+ size 1000088
unet/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.28.0.dev0",
4
- "_name_or_path": "runwayml/stable-diffusion-v1-5",
5
  "act_fn": "silu",
6
  "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.28.0.dev0",
4
+ "_name_or_path": "instruct-pix2pix-model/checkpoint-20000",
5
  "act_fn": "silu",
6
  "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a405b4ae3686d437b014f0b57fd0c6b17e30e1ce6c02422916b086b7d802c6ac
3
  size 3438213624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385fd71c886c06fcfc261221cb30c5efd429148ecc3594f6c1a3f7f6407b4a20
3
  size 3438213624