Hugging Face's logo

c-eshih
/
human_stable_diffusion_concat_loss

Diffusers
TensorBoard
Safetensors
StableDiffusionInstructPix2PixPipeline
Model card Files Metrics Community
c-eshih commited on
Commit
0e1dbf2
•
1 Parent(s): 638f3d0

End of training

Browse files
Files changed (20) hide show
  1. checkpoint-6300/optimizer.bin +3 -0
  2. checkpoint-6300/random_states_0.pkl +3 -0
  3. checkpoint-6300/scaler.pt +3 -0
  4. checkpoint-6300/scheduler.bin +3 -0
  5. checkpoint-6300/unet/config.json +68 -0
  6. checkpoint-6300/unet/diffusion_pytorch_model.safetensors +3 -0
  7. checkpoint-6400/optimizer.bin +3 -0
  8. checkpoint-6400/random_states_0.pkl +3 -0
  9. checkpoint-6400/scaler.pt +3 -0
  10. checkpoint-6400/scheduler.bin +3 -0
  11. checkpoint-6400/unet/config.json +68 -0
  12. checkpoint-6400/unet/diffusion_pytorch_model.safetensors +3 -0
  13. logs/instruct-pix2pix/1720770182.9498885/events.out.tfevents.1720770182.ambus-algoq6069.621610.1 +3 -0
  14. logs/instruct-pix2pix/1720770182.9530385/hparams.yml +52 -0
  15. logs/instruct-pix2pix/1720821115.883535/events.out.tfevents.1720821115.ambus-algoq6069.902168.1 +3 -0
  16. logs/instruct-pix2pix/1720821115.8871148/hparams.yml +52 -0
  17. logs/instruct-pix2pix/events.out.tfevents.1720770182.ambus-algoq6069.621610.0 +3 -0
  18. logs/instruct-pix2pix/events.out.tfevents.1720821115.ambus-algoq6069.902168.0 +3 -0
  19. unet/config.json +1 -1
  20. unet/diffusion_pytorch_model.safetensors +1 -1
checkpoint-6300/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fce705cc4d6e4cdc27f4dfc087a9e4c60bf78ae536b70d5b0aac0fdc81493ced
3
+ size 6876874964
checkpoint-6300/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b6926eb004edada48251960b70b5ec25476b12365c94537ce4c598642db609
3
+ size 15060
checkpoint-6300/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1657fcbd72a2c6c4189fde908ab547d31f4a9ed9ac401b88a1eca57254332722
3
+ size 988
checkpoint-6300/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:525e1bed668d64c86c0cb4ac0b700ffbca7018a13429e6cd1ed025f7943a841b
3
+ size 1000
checkpoint-6300/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "./human_stable_diffusion_concat_loss/checkpoint-5600",
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": 9,
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-6300/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6036a20f77c3632ae6970bde8ca167dc3c6776872344679ca5a6a4072612323d
3
+ size 3438225152
checkpoint-6400/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84fde58583a6939b5f0ea143ce53faa7a2805925d4c4a75b3e1d6d46714df4cd
3
+ size 6876874964
checkpoint-6400/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c0808c0ea235040edabba901643ef1467fb4e1c286fb2ae1461dbe36d52402
3
+ size 15060
checkpoint-6400/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd7cb9add0c22ced4226e4e6317931f94844dc550a23ed36310554c33ecabada
3
+ size 988
checkpoint-6400/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:379f46372dec7ec764bd8aac2ed1e8e972253c182aa29d73273cf9af250100cb
3
+ size 1000
checkpoint-6400/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "./human_stable_diffusion_concat_loss/checkpoint-5600",
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": 9,
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-6400/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca3a003031a58ab34d2f8515f6a293be234c2c092cd802de6b6f4e2ab988795
3
+ size 3438225152
logs/instruct-pix2pix/1720770182.9498885/events.out.tfevents.1720770182.ambus-algoq6069.621610.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d3024ead1f53fa3828836b61fc81cbcc80fa42fc055eb987ffe5a9628a4a920
3
+ size 2558
logs/instruct-pix2pix/1720770182.9530385/hparams.yml ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 100
9
+ checkpoints_total_limit: 2
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
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
+ mask_image_column: mask_image
27
+ max_grad_norm: 1.0
28
+ max_train_samples: null
29
+ max_train_steps: 6440
30
+ mixed_precision: fp16
31
+ non_ema_revision: null
32
+ num_train_epochs: 40
33
+ num_validation_images: 4
34
+ original_image_column: input_image
35
+ output_dir: ./human_stable_diffusion_concat_loss
36
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
37
+ push_to_hub: true
38
+ random_flip: true
39
+ report_to: tensorboard
40
+ resolution: 256
41
+ resume_from_checkpoint: latest
42
+ revision: null
43
+ scale_lr: false
44
+ seed: 42
45
+ train_batch_size: 4
46
+ train_data_dir: ./dataset_mask_new/train
47
+ use_8bit_adam: false
48
+ use_ema: false
49
+ val_image_url: null
50
+ validation_epochs: 1
51
+ validation_prompt: null
52
+ variant: null
logs/instruct-pix2pix/1720821115.883535/events.out.tfevents.1720821115.ambus-algoq6069.902168.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e365ea59ed0932ecc14e2dd3ea36798e6305ef9d3a1820a94bd4daa3b91025
3
+ size 2558
logs/instruct-pix2pix/1720821115.8871148/hparams.yml ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 100
9
+ checkpoints_total_limit: 2
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
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
+ mask_image_column: mask_image
27
+ max_grad_norm: 1.0
28
+ max_train_samples: null
29
+ max_train_steps: 6440
30
+ mixed_precision: fp16
31
+ non_ema_revision: null
32
+ num_train_epochs: 40
33
+ num_validation_images: 4
34
+ original_image_column: input_image
35
+ output_dir: ./human_stable_diffusion_concat_loss
36
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
37
+ push_to_hub: true
38
+ random_flip: true
39
+ report_to: tensorboard
40
+ resolution: 256
41
+ resume_from_checkpoint: latest
42
+ revision: null
43
+ scale_lr: false
44
+ seed: 42
45
+ train_batch_size: 4
46
+ train_data_dir: ./dataset_mask_new/train
47
+ use_8bit_adam: false
48
+ use_ema: false
49
+ val_image_url: null
50
+ validation_epochs: 1
51
+ validation_prompt: null
52
+ variant: null
logs/instruct-pix2pix/events.out.tfevents.1720770182.ambus-algoq6069.621610.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1089344fb7bae7ef818476a9812a461a892c4985a9d7f5881a8066cfc7d94d40
3
+ size 199665
logs/instruct-pix2pix/events.out.tfevents.1720821115.ambus-algoq6069.902168.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e20c71426f511758865aeeefc841308c5f9089297230c7fbb2b225ebc863dc
3
+ size 41248
unet/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.29.0.dev0",
4
- "_name_or_path": "./human_stable_diffusion_concat_loss/checkpoint-1100",
5
  "act_fn": "silu",
6
  "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "./human_stable_diffusion_concat_loss/checkpoint-5600",
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:e1ebe0bcf2026476d8a6ba77272d589e4e87ebc5652765a65cfc0bc64f5224a3
3
  size 3438225152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770cee2507783eb84149b2b19803edbc4b7857db107ceb0a746515e6c7dd604d
3
  size 3438225152