Hugging Face's logo

ivillar
/
riff-pix2pix-test

Diffusers
TensorBoard
Safetensors
StableDiffusionInstructPix2PixPipeline
Model card Files Metrics Community
ivillar commited on
Commit
91dd526
·
1 Parent(s): 01db879

End of training

Browse files
Files changed (33) hide show
  1. logs/instruct-pix2pix/1701422739.6678472/events.out.tfevents.1701422739.ip-172-31-41-114.66407.1 +3 -0
  2. logs/instruct-pix2pix/1701422739.6693673/hparams.yml +50 -0
  3. logs/instruct-pix2pix/1701423024.789818/events.out.tfevents.1701423024.ip-172-31-41-114.67545.1 +3 -0
  4. logs/instruct-pix2pix/1701423024.7914062/hparams.yml +50 -0
  5. logs/instruct-pix2pix/1701423399.6441886/events.out.tfevents.1701423399.ip-172-31-41-114.69133.1 +3 -0
  6. logs/instruct-pix2pix/1701423399.6456625/hparams.yml +50 -0
  7. logs/instruct-pix2pix/1701423486.420575/events.out.tfevents.1701423486.ip-172-31-41-114.69637.1 +3 -0
  8. logs/instruct-pix2pix/1701423486.4222963/hparams.yml +50 -0
  9. logs/instruct-pix2pix/1701423934.0894911/events.out.tfevents.1701423934.ip-172-31-41-114.71557.1 +3 -0
  10. logs/instruct-pix2pix/1701423934.0912156/hparams.yml +50 -0
  11. logs/instruct-pix2pix/1701424042.3573377/events.out.tfevents.1701424042.ip-172-31-41-114.72133.1 +3 -0
  12. logs/instruct-pix2pix/1701424042.3588028/hparams.yml +50 -0
  13. logs/instruct-pix2pix/1701424399.811622/events.out.tfevents.1701424399.ip-172-31-41-114.73580.1 +3 -0
  14. logs/instruct-pix2pix/1701424399.8130803/hparams.yml +50 -0
  15. logs/instruct-pix2pix/1701424478.4684424/events.out.tfevents.1701424478.ip-172-31-41-114.74074.1 +3 -0
  16. logs/instruct-pix2pix/1701424478.47018/hparams.yml +50 -0
  17. logs/instruct-pix2pix/events.out.tfevents.1701422735.ip-172-31-41-114.66407.0 +3 -0
  18. logs/instruct-pix2pix/events.out.tfevents.1701423020.ip-172-31-41-114.67545.0 +3 -0
  19. logs/instruct-pix2pix/events.out.tfevents.1701423395.ip-172-31-41-114.69133.0 +3 -0
  20. logs/instruct-pix2pix/events.out.tfevents.1701423482.ip-172-31-41-114.69637.0 +3 -0
  21. logs/instruct-pix2pix/events.out.tfevents.1701423929.ip-172-31-41-114.71557.0 +3 -0
  22. logs/instruct-pix2pix/events.out.tfevents.1701424038.ip-172-31-41-114.72133.0 +3 -0
  23. logs/instruct-pix2pix/events.out.tfevents.1701424395.ip-172-31-41-114.73580.0 +3 -0
  24. logs/instruct-pix2pix/events.out.tfevents.1701424474.ip-172-31-41-114.74074.0 +3 -0
  25. model_index.json +4 -4
  26. safety_checker/config.json +28 -0
  27. safety_checker/model.safetensors +3 -0
  28. text_encoder/config.json +2 -2
  29. text_encoder/model.safetensors +2 -2
  30. unet/config.json +1 -1
  31. unet/diffusion_pytorch_model.safetensors +1 -1
  32. vae/config.json +1 -1
  33. vae/diffusion_pytorch_model.safetensors +2 -2
logs/instruct-pix2pix/1701422739.6678472/events.out.tfevents.1701422739.ip-172-31-41-114.66407.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32db93b4d18bfc9696e162130e6ec8e37c2fecf0817f222777130b9ab99d24fb
3
+ size 2522
logs/instruct-pix2pix/1701422739.6693673/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: cache
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: ivillar/mdb-mc-mtt-spec-pix2pix
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 1
18
+ gradient_checkpointing: true
19
+ hub_model_id: ivillar/riff-pix2pix-test
20
+ hub_token: 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
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 10
33
+ original_image_column: original_image
34
+ output_dir: model
35
+ pretrained_model_name_or_path: zachary-shah/riff-pix2pix-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: all
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
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/1701423024.789818/events.out.tfevents.1701423024.ip-172-31-41-114.67545.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b931edc430c7a358e062db42a5175db153e297027df7eb028800a59e63763e0
3
+ size 2524
logs/instruct-pix2pix/1701423024.7914062/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: cache
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: zachary-shah/musdb18-spec-pix2pix
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 1
18
+ gradient_checkpointing: true
19
+ hub_model_id: ivillar/riff-pix2pix-test
20
+ hub_token: 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
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 10
33
+ original_image_column: original_image
34
+ output_dir: model
35
+ pretrained_model_name_or_path: zachary-shah/riff-pix2pix-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: all
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
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/1701423399.6441886/events.out.tfevents.1701423399.ip-172-31-41-114.69133.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:443491b7cb1ae80843d522e4447ac041497d777dc1c27401fc467666b9f0e1ef
3
+ size 2524
logs/instruct-pix2pix/1701423399.6456625/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: cache
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: zachary-shah/musdb18-spec-pix2pix
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 1
18
+ gradient_checkpointing: true
19
+ hub_model_id: ivillar/riff-pix2pix-test
20
+ hub_token: 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
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 10
33
+ original_image_column: original_image
34
+ output_dir: model
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: all
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
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/1701423486.420575/events.out.tfevents.1701423486.ip-172-31-41-114.69637.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24307a2deefebfb0756d4e94d9356bc628e39ef87aa0eac31fd0db7125144f27
3
+ size 2524
logs/instruct-pix2pix/1701423486.4222963/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: cache
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: zachary-shah/musdb18-spec-pix2pix
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 1
18
+ gradient_checkpointing: true
19
+ hub_model_id: ivillar/riff-pix2pix-test
20
+ hub_token: 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
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 10
33
+ original_image_column: original_image
34
+ output_dir: model
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: all
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
44
+ train_batch_size: 1
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/1701423934.0894911/events.out.tfevents.1701423934.ip-172-31-41-114.71557.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d5cc9ca927f202385ffd56e86324deebdee9deaee4759800c42840625b5b0af
3
+ size 2524
logs/instruct-pix2pix/1701423934.0912156/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: cache
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: zachary-shah/musdb18-spec-pix2pix
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 1
18
+ gradient_checkpointing: true
19
+ hub_model_id: ivillar/riff-pix2pix-test
20
+ hub_token: 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
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 10
33
+ original_image_column: original_image
34
+ output_dir: model
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: all
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
44
+ train_batch_size: 1
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/1701424042.3573377/events.out.tfevents.1701424042.ip-172-31-41-114.72133.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0220af1b227e6c4e27b699fdab1f1c6fc20f6a20ad3a9fddf7df06b41ae9a05
3
+ size 2524
logs/instruct-pix2pix/1701424042.3588028/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: cache
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: zachary-shah/musdb18-spec-pix2pix
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 1
18
+ gradient_checkpointing: true
19
+ hub_model_id: ivillar/riff-pix2pix-test
20
+ hub_token: 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
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 10
33
+ original_image_column: original_image
34
+ output_dir: model
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: all
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
44
+ train_batch_size: 1
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/1701424399.811622/events.out.tfevents.1701424399.ip-172-31-41-114.73580.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:650be6c9f8fc2e8ba5c82f4d3a9e4d4874a7cc605b82e94e85660335d3286750
3
+ size 2524
logs/instruct-pix2pix/1701424399.8130803/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: cache
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: zachary-shah/musdb18-spec-pix2pix
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 1
18
+ gradient_checkpointing: true
19
+ hub_model_id: ivillar/riff-pix2pix-test
20
+ hub_token: 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
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 10
33
+ original_image_column: original_image
34
+ output_dir: model
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: all
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
44
+ train_batch_size: 1
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/1701424478.4684424/events.out.tfevents.1701424478.ip-172-31-41-114.74074.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef3bdbe77fdf367e1be022ff64954d33fe6c766b6b8db8529ba70627efe5406
3
+ size 2524
logs/instruct-pix2pix/1701424478.47018/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: cache
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: zachary-shah/musdb18-spec-pix2pix
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 1
18
+ gradient_checkpointing: true
19
+ hub_model_id: ivillar/riff-pix2pix-test
20
+ hub_token: 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
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 10
33
+ original_image_column: original_image
34
+ output_dir: model
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: all
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
44
+ train_batch_size: 1
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/events.out.tfevents.1701422735.ip-172-31-41-114.66407.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737323f1ff44020c273032b5f598e101968076486efae11583705cc508420ad9
3
+ size 136
logs/instruct-pix2pix/events.out.tfevents.1701423020.ip-172-31-41-114.67545.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc98d29b8c3b88ac17b2359a6c4cc7a1799af4912797b4e61a88c223fbe1b6f
3
+ size 136
logs/instruct-pix2pix/events.out.tfevents.1701423395.ip-172-31-41-114.69133.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8604f3747ff8e3e1efe9513bdd2fad2f67edf64639952743a341efc4bd417cc1
3
+ size 136
logs/instruct-pix2pix/events.out.tfevents.1701423482.ip-172-31-41-114.69637.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d540f4b67ea5a39f572964a336799facc6dc2e97ed4f88bbd44113db0f96f31f
3
+ size 232
logs/instruct-pix2pix/events.out.tfevents.1701423929.ip-172-31-41-114.71557.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1778653e1e412c7c89f06729e843e0028029cf4af627af6bf5eab0ce43090346
3
+ size 232
logs/instruct-pix2pix/events.out.tfevents.1701424038.ip-172-31-41-114.72133.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827d592ee0aa3ce61889d20ade951399e7d765f271844e2da31dbd85b358a16a
3
+ size 232
logs/instruct-pix2pix/events.out.tfevents.1701424395.ip-172-31-41-114.73580.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae832708965833fdfcfe7899d6e4c3fcdf0cee94bda1b5f29b1e5ac679f77df
3
+ size 232
logs/instruct-pix2pix/events.out.tfevents.1701424474.ip-172-31-41-114.74074.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f547a0a56e368280bde58f92267c128f147e871eeaa24a80908084a78402bc2
3
+ size 232
model_index.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
  "_class_name": "StableDiffusionInstructPix2PixPipeline",
3
  "_diffusers_version": "0.24.0",
4
- "_name_or_path": "zachary-shah/riff-pix2pix-v1",
5
  "feature_extractor": [
6
  "transformers",
7
  "CLIPImageProcessor"
8
  ],
9
- "requires_safety_checker": false,
10
  "safety_checker": [
11
- null,
12
- null
13
  ],
14
  "scheduler": [
15
  "diffusers",
 
1
  {
2
  "_class_name": "StableDiffusionInstructPix2PixPipeline",
3
  "_diffusers_version": "0.24.0",
4
+ "_name_or_path": "riffusion/riffusion-model-v1",
5
  "feature_extractor": [
6
  "transformers",
7
  "CLIPImageProcessor"
8
  ],
9
+ "requires_safety_checker": true,
10
  "safety_checker": [
11
+ "stable_diffusion",
12
+ "StableDiffusionSafetyChecker"
13
  ],
14
  "scheduler": [
15
  "diffusers",
safety_checker/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--riffusion--riffusion-model-v1/snapshots/8f2e752c74e8316c6eb4fdaa6598a46ce1d88af5/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": "4.35.2",
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:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
3
+ size 1215979664
text_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "zachary-shah/riff-pix2pix-v1",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -19,7 +19,7 @@
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
- "torch_dtype": "float32",
23
  "transformers_version": "4.35.2",
24
  "vocab_size": 49408
25
  }
 
1
  {
2
+ "_name_or_path": "riffusion/riffusion-model-v1",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
 
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
+ "torch_dtype": "float16",
23
  "transformers_version": "4.35.2",
24
  "vocab_size": 49408
25
  }
text_encoder/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c3d6454dd2d23414b56aa1b5858a72487a656937847b6fea8d0606d7a42cdbc
3
- size 492265168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
3
+ size 246144152
unet/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.24.0",
4
- "_name_or_path": "zachary-shah/riff-pix2pix-v1",
5
  "act_fn": "silu",
6
  "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.24.0",
4
+ "_name_or_path": "riffusion/riffusion-model-v1",
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 sha256:1191a31e7fd0e730329a46419f473d4aa68fdd73fe78f297d6db96abd6a04b85
3
  size 3438213624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab136ca785d023925def955c9e96d6257c3777ad973703ae1a351eaa9e1fcd8
3
  size 3438213624
vae/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.24.0",
4
- "_name_or_path": "zachary-shah/riff-pix2pix-v1",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.24.0",
4
+ "_name_or_path": "riffusion/riffusion-model-v1",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
vae/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35710aa69434a828cf1135b421ce0f88369ebe7c274fa248270e4c4af965aaf4
3
- size 334643268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
3
+ size 167335342