zachary-shah commited on
Commit
74789c0
1 Parent(s): 975682b

Upload folder using huggingface_hub

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-300000/optimizer.bin +3 -0
  2. checkpoint-300000/random_states_0.pkl +3 -0
  3. checkpoint-300000/scaler.pt +3 -0
  4. checkpoint-300000/scheduler.bin +3 -0
  5. checkpoint-300000/unet/config.json +62 -0
  6. checkpoint-300000/unet/diffusion_pytorch_model.bin +3 -0
  7. config.json +62 -0
  8. feature_extractor/preprocessor_config.json +28 -0
  9. logs/instruct-pix2pix/1686024460.013109/events.out.tfevents.1686024460.ip-172-31-28-175.ec2.internal.5327.1 +3 -0
  10. logs/instruct-pix2pix/1686024460.0144317/hparams.yml +50 -0
  11. logs/instruct-pix2pix/1686024636.282702/events.out.tfevents.1686024636.ip-172-31-28-175.ec2.internal.6891.1 +3 -0
  12. logs/instruct-pix2pix/1686024636.2839978/hparams.yml +50 -0
  13. logs/instruct-pix2pix/1686024669.0956256/events.out.tfevents.1686024669.ip-172-31-28-175.ec2.internal.7120.1 +3 -0
  14. logs/instruct-pix2pix/1686024669.0970294/hparams.yml +50 -0
  15. logs/instruct-pix2pix/1686024697.2151372/events.out.tfevents.1686024697.ip-172-31-28-175.ec2.internal.7629.1 +3 -0
  16. logs/instruct-pix2pix/1686024697.2164345/hparams.yml +50 -0
  17. logs/instruct-pix2pix/1686024729.483795/events.out.tfevents.1686024729.ip-172-31-28-175.ec2.internal.8161.1 +3 -0
  18. logs/instruct-pix2pix/1686024729.4851048/hparams.yml +50 -0
  19. logs/instruct-pix2pix/1686251434.2604456/events.out.tfevents.1686251434.ip-172-31-28-175.ec2.internal.7700.1 +3 -0
  20. logs/instruct-pix2pix/1686251434.2618048/hparams.yml +50 -0
  21. logs/instruct-pix2pix/1686251604.0436833/events.out.tfevents.1686251604.ip-172-31-28-175.ec2.internal.8878.1 +3 -0
  22. logs/instruct-pix2pix/1686251604.045071/hparams.yml +50 -0
  23. logs/instruct-pix2pix/1686251721.46846/events.out.tfevents.1686251721.ip-172-31-28-175.ec2.internal.9638.1 +3 -0
  24. logs/instruct-pix2pix/1686251721.4697907/hparams.yml +50 -0
  25. logs/instruct-pix2pix/1686251843.1085622/events.out.tfevents.1686251843.ip-172-31-28-175.ec2.internal.10427.1 +3 -0
  26. logs/instruct-pix2pix/1686251843.1098614/hparams.yml +50 -0
  27. logs/instruct-pix2pix/1686252476.5714889/events.out.tfevents.1686252476.ip-172-31-28-175.ec2.internal.14778.1 +3 -0
  28. logs/instruct-pix2pix/1686252476.5728323/hparams.yml +50 -0
  29. logs/instruct-pix2pix/1686252763.501972/events.out.tfevents.1686252763.ip-172-31-28-175.ec2.internal.16627.1 +3 -0
  30. logs/instruct-pix2pix/1686252763.5033057/hparams.yml +50 -0
  31. logs/instruct-pix2pix/1686253046.6994145/events.out.tfevents.1686253046.ip-172-31-28-175.ec2.internal.18316.1 +3 -0
  32. logs/instruct-pix2pix/1686253046.7006776/hparams.yml +50 -0
  33. logs/instruct-pix2pix/events.out.tfevents.1686024460.ip-172-31-28-175.ec2.internal.5327.0 +3 -0
  34. logs/instruct-pix2pix/events.out.tfevents.1686024636.ip-172-31-28-175.ec2.internal.6891.0 +3 -0
  35. logs/instruct-pix2pix/events.out.tfevents.1686024669.ip-172-31-28-175.ec2.internal.7120.0 +3 -0
  36. logs/instruct-pix2pix/events.out.tfevents.1686024697.ip-172-31-28-175.ec2.internal.7629.0 +3 -0
  37. logs/instruct-pix2pix/events.out.tfevents.1686024729.ip-172-31-28-175.ec2.internal.8161.0 +3 -0
  38. logs/instruct-pix2pix/events.out.tfevents.1686251434.ip-172-31-28-175.ec2.internal.7700.0 +3 -0
  39. logs/instruct-pix2pix/events.out.tfevents.1686251604.ip-172-31-28-175.ec2.internal.8878.0 +3 -0
  40. logs/instruct-pix2pix/events.out.tfevents.1686251721.ip-172-31-28-175.ec2.internal.9638.0 +3 -0
  41. logs/instruct-pix2pix/events.out.tfevents.1686251843.ip-172-31-28-175.ec2.internal.10427.0 +3 -0
  42. logs/instruct-pix2pix/events.out.tfevents.1686252476.ip-172-31-28-175.ec2.internal.14778.0 +3 -0
  43. logs/instruct-pix2pix/events.out.tfevents.1686252763.ip-172-31-28-175.ec2.internal.16627.0 +3 -0
  44. logs/instruct-pix2pix/events.out.tfevents.1686253046.ip-172-31-28-175.ec2.internal.18316.0 +3 -0
  45. model_index.json +33 -0
  46. safety_checker/config.json +168 -0
  47. safety_checker/pytorch_model.bin +3 -0
  48. scheduler/scheduler_config.json +13 -0
  49. text_encoder/config.json +25 -0
  50. text_encoder/pytorch_model.bin +3 -0
checkpoint-300000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dea3dfef93a3d79b99a94113c00e309d5b389b997a4f9b7622766d6c86033d34
3
+ size 6876841875
checkpoint-300000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38634cfb84d7b7fae2cf0a0bc74da16920ac62feeabffdf530412d95af027691
3
+ size 14599
checkpoint-300000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad22c3c5ec18fbcefcdeaed8966966b55e7bbbb3f35933d442f9fa0eb43958b4
3
+ size 557
checkpoint-300000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52884016fcba3f7c2b382b23b287311c9ff6eac8f40c3d403a4e9b5610add0ad
3
+ size 563
checkpoint-300000/unet/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "_name_or_path": "/data/pix2pix-riff-ckpt/checkpoint-180000",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "attention_head_dim": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "center_input_sample": false,
16
+ "class_embed_type": null,
17
+ "class_embeddings_concat": false,
18
+ "conv_in_kernel": 3,
19
+ "conv_out_kernel": 3,
20
+ "cross_attention_dim": 768,
21
+ "cross_attention_norm": null,
22
+ "down_block_types": [
23
+ "CrossAttnDownBlock2D",
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "DownBlock2D"
27
+ ],
28
+ "downsample_padding": 1,
29
+ "dual_cross_attention": false,
30
+ "encoder_hid_dim": null,
31
+ "encoder_hid_dim_type": null,
32
+ "flip_sin_to_cos": true,
33
+ "freq_shift": 0,
34
+ "in_channels": 8,
35
+ "layers_per_block": 2,
36
+ "mid_block_only_cross_attention": null,
37
+ "mid_block_scale_factor": 1,
38
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
39
+ "norm_eps": 1e-05,
40
+ "norm_num_groups": 32,
41
+ "num_class_embeds": null,
42
+ "only_cross_attention": false,
43
+ "out_channels": 4,
44
+ "projection_class_embeddings_input_dim": null,
45
+ "resnet_out_scale_factor": 1.0,
46
+ "resnet_skip_time_act": false,
47
+ "resnet_time_scale_shift": "default",
48
+ "sample_size": 32,
49
+ "time_cond_proj_dim": null,
50
+ "time_embedding_act_fn": null,
51
+ "time_embedding_dim": null,
52
+ "time_embedding_type": "positional",
53
+ "timestep_post_act": null,
54
+ "up_block_types": [
55
+ "UpBlock2D",
56
+ "CrossAttnUpBlock2D",
57
+ "CrossAttnUpBlock2D",
58
+ "CrossAttnUpBlock2D"
59
+ ],
60
+ "upcast_attention": false,
61
+ "use_linear_projection": false
62
+ }
checkpoint-300000/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd649c4136eec574184838a8a8d3a24d9c2243ed5e8b181aa1856840acdcdf2
3
+ size 3438422053
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "_name_or_path": "riffusion/riffusion-model-v1",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "attention_head_dim": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "center_input_sample": false,
16
+ "class_embed_type": null,
17
+ "class_embeddings_concat": false,
18
+ "conv_in_kernel": 3,
19
+ "conv_out_kernel": 3,
20
+ "cross_attention_dim": 768,
21
+ "cross_attention_norm": null,
22
+ "down_block_types": [
23
+ "CrossAttnDownBlock2D",
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "DownBlock2D"
27
+ ],
28
+ "downsample_padding": 1,
29
+ "dual_cross_attention": false,
30
+ "encoder_hid_dim": null,
31
+ "encoder_hid_dim_type": null,
32
+ "flip_sin_to_cos": true,
33
+ "freq_shift": 0,
34
+ "in_channels": 8,
35
+ "layers_per_block": 2,
36
+ "mid_block_only_cross_attention": null,
37
+ "mid_block_scale_factor": 1,
38
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
39
+ "norm_eps": 1e-05,
40
+ "norm_num_groups": 32,
41
+ "num_class_embeds": null,
42
+ "only_cross_attention": false,
43
+ "out_channels": 4,
44
+ "projection_class_embeddings_input_dim": null,
45
+ "resnet_out_scale_factor": 1.0,
46
+ "resnet_skip_time_act": false,
47
+ "resnet_time_scale_shift": "default",
48
+ "sample_size": 32,
49
+ "time_cond_proj_dim": null,
50
+ "time_embedding_act_fn": null,
51
+ "time_embedding_dim": null,
52
+ "time_embedding_type": "positional",
53
+ "timestep_post_act": null,
54
+ "up_block_types": [
55
+ "UpBlock2D",
56
+ "CrossAttnUpBlock2D",
57
+ "CrossAttnUpBlock2D",
58
+ "CrossAttnUpBlock2D"
59
+ ],
60
+ "upcast_attention": false,
61
+ "use_linear_projection": false
62
+ }
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPImageProcessor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
logs/instruct-pix2pix/1686024460.013109/events.out.tfevents.1686024460.ip-172-31-28-175.ec2.internal.5327.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70e92e71f365ffe4f9f5b9805891bb5a3f26e8133f28c095459b182b1fb8a9c7
3
+ size 2517
logs/instruct-pix2pix/1686024460.0144317/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: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
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: zachary-shah/riff-pix2pix-v1
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: 3155600
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 100
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: /data/pix2pix-riff-model
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
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/1686024636.282702/events.out.tfevents.1686024636.ip-172-31-28-175.ec2.internal.6891.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094cb4a49399d47a411c7939816a49908f0fe276d67f425c369674d3ca11a6cb
3
+ size 2572
logs/instruct-pix2pix/1686024636.2839978/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: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
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: zachary-shah/riff-pix2pix-v1
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: 10000
28
+ max_train_steps: 500000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 100
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: /data/pix2pix-riff-model
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
44
+ train_batch_size: 2
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/1686024669.0956256/events.out.tfevents.1686024669.ip-172-31-28-175.ec2.internal.7120.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb32fc8d68d140bffed2b80231a3fada25d3c6f11305d1799da8b02351c33601
3
+ size 2572
logs/instruct-pix2pix/1686024669.0970294/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: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 16
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: zachary-shah/riff-pix2pix-v1
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: 10000
28
+ max_train_steps: 500000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 100
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: /data/pix2pix-riff-model
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
44
+ train_batch_size: 2
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/1686024697.2151372/events.out.tfevents.1686024697.ip-172-31-28-175.ec2.internal.7629.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeec7568326ac022e03c6034b9d07382fb876994675baa9ffbc5f2bba04049e3
3
+ size 2572
logs/instruct-pix2pix/1686024697.2164345/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: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 16
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: false
19
+ hub_model_id: zachary-shah/riff-pix2pix-v1
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: 10000
28
+ max_train_steps: 500000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 100
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: /data/pix2pix-riff-model
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
44
+ train_batch_size: 2
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/1686024729.483795/events.out.tfevents.1686024729.ip-172-31-28-175.ec2.internal.8161.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d687072fe6406428b40e46c1d762b6e271ff2db85935522242e6eb58b56f80
3
+ size 2572
logs/instruct-pix2pix/1686024729.4851048/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: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 16
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: false
19
+ hub_model_id: zachary-shah/riff-pix2pix-v1
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: 10000
28
+ max_train_steps: 250000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 100
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: /data/pix2pix-riff-model
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
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/1686251434.2604456/events.out.tfevents.1686251434.ip-172-31-28-175.ec2.internal.7700.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec566f287a78901fc6b296e67adc61a4739e24e9c3dc7c8f0d3bd000845b33fc
3
+ size 2616
logs/instruct-pix2pix/1686251434.2618048/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: null
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 16
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: false
19
+ hub_model_id: zachary-shah/riff-pix2pix-v1
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: 90000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 12
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: /data/pix2pix-riff-ckpt
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /data/pix2pix-riff-ckpt/checkpoint-180000/
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/1686251604.0436833/events.out.tfevents.1686251604.ip-172-31-28-175.ec2.internal.8878.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959d06c122d8f48e5a0173d3daa861a6ea664809a76a843b33664e5093fb4fd8
3
+ size 2616
logs/instruct-pix2pix/1686251604.045071/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: null
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 16
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: false
19
+ hub_model_id: zachary-shah/riff-pix2pix-v1
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: 90000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 12
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: /data/pix2pix-riff-ckpt
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /data/pix2pix-riff-ckpt/checkpoint-180000/
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/1686251721.46846/events.out.tfevents.1686251721.ip-172-31-28-175.ec2.internal.9638.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eaef5f7ffc6658be93bef1e6a97c2e1ecd156b65634441d56d4da7e750dd940
3
+ size 2616
logs/instruct-pix2pix/1686251721.4697907/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: null
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 16
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: false
19
+ hub_model_id: zachary-shah/riff-pix2pix-v1
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: 90000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 12
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: /data/pix2pix-riff-ckpt
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /data/pix2pix-riff-ckpt/checkpoint-180000/
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/1686251843.1085622/events.out.tfevents.1686251843.ip-172-31-28-175.ec2.internal.10427.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5c4a7118afbdd52b0714d114e87336d5fceb1c07aebe2ccef38f5b9f93edf4
3
+ size 2616
logs/instruct-pix2pix/1686251843.1098614/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: null
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 16
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: false
19
+ hub_model_id: zachary-shah/riff-pix2pix-v1
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: 90000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 12
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: /data/pix2pix-riff-ckpt
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /data/pix2pix-riff-ckpt/checkpoint-180000/
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/1686252476.5714889/events.out.tfevents.1686252476.ip-172-31-28-175.ec2.internal.14778.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e714f4134332fdb3873a3cc9cb6fa814eb068953d2125a9a3419d7c48abbe7e3
3
+ size 2580
logs/instruct-pix2pix/1686252476.5728323/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: null
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 16
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: false
19
+ hub_model_id: zachary-shah/riff-pix2pix-v1
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: 90000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 12
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: /data/pix2pix-riff-ckpt
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: latest
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/1686252763.501972/events.out.tfevents.1686252763.ip-172-31-28-175.ec2.internal.16627.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8673a3c8e68994f0f95e1949a8bb7b34bccb5508bbda13d15400792f043c77e
3
+ size 2445
logs/instruct-pix2pix/1686252763.5033057/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: null
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 16
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: false
19
+ hub_model_id: null
20
+ hub_token: null
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: 90000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 12
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: /data/pix2pix-riff-ckpt
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: false
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: latest
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/1686253046.6994145/events.out.tfevents.1686253046.ip-172-31-28-175.ec2.internal.18316.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42ae038d19aaaaeb63193e36fbf8877abff72d4b6b1a4e281d91a73fcb0574f1
3
+ size 2445
logs/instruct-pix2pix/1686253046.7006776/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: null
7
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 16
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: false
19
+ hub_model_id: null
20
+ hub_token: null
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: 300000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 39
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: /data/pix2pix-riff-ckpt
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: false
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: latest
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/events.out.tfevents.1686024460.ip-172-31-28-175.ec2.internal.5327.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0bc80c7606adc4c35795167230ce29abd5c260f81e5b190fd6e30892c3c4f49
3
+ size 10594
logs/instruct-pix2pix/events.out.tfevents.1686024636.ip-172-31-28-175.ec2.internal.6891.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ce01e3cc5a9de6da973a097506826d35ff7d86f9372015074e384382eb9690
3
+ size 1048
logs/instruct-pix2pix/events.out.tfevents.1686024669.ip-172-31-28-175.ec2.internal.7120.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee4749ebf1ab093ec0b7e0c39ac0a15194303b638bf43178f2240b114d42a363
3
+ size 760
logs/instruct-pix2pix/events.out.tfevents.1686024697.ip-172-31-28-175.ec2.internal.7629.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fccb7a532594f91451ae0556fc5164771664566a587b6ff818411116c9046bc6
3
+ size 1096
logs/instruct-pix2pix/events.out.tfevents.1686024729.ip-172-31-28-175.ec2.internal.8161.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d01329bca2af463822c468097e6aee83f6f396821a9068e4270ea10cc5761ab1
3
+ size 9233578
logs/instruct-pix2pix/events.out.tfevents.1686251434.ip-172-31-28-175.ec2.internal.7700.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6302e2e10b20728537497f5440de51c95a733b184a23174eb805d46e583408a
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1686251604.ip-172-31-28-175.ec2.internal.8878.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b58d92dc8f123b31126b909885c3bfc2377b964f7a0139b56d32b847cad5fd6
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1686251721.ip-172-31-28-175.ec2.internal.9638.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f71e6a69e224c8f1ddf62484791c965bfb0f11928358fc86ac6b8b9e6409b2e4
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1686251843.ip-172-31-28-175.ec2.internal.10427.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faf3444a25ace3559de379bae211bac1d761309f83a285681655f8109500e7d9
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1686252476.ip-172-31-28-175.ec2.internal.14778.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d145d31694b71d66fa868fd5ff08be6369fa310902405247a1eeaf1a0a2c9441
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1686252763.ip-172-31-28-175.ec2.internal.16627.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc48a70440cc2e40e336598cf0212c81e7d363e735f70f16f0937a309cb5965
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1686253046.ip-172-31-28-175.ec2.internal.18316.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a871741152bd129716652a92867928d464780d484590fc46e2d333373ce26c99
3
+ size 6000088
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionInstructPix2PixPipeline",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPImageProcessor"
7
+ ],
8
+ "requires_safety_checker": true,
9
+ "safety_checker": [
10
+ "stable_diffusion",
11
+ "StableDiffusionSafetyChecker"
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "PNDMScheduler"
16
+ ],
17
+ "text_encoder": [
18
+ "transformers",
19
+ "CLIPTextModel"
20
+ ],
21
+ "tokenizer": [
22
+ "transformers",
23
+ "CLIPTokenizer"
24
+ ],
25
+ "unet": [
26
+ "diffusers",
27
+ "UNet2DConditionModel"
28
+ ],
29
+ "vae": [
30
+ "diffusers",
31
+ "AutoencoderKL"
32
+ ]
33
+ }
safety_checker/config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "8f2e752c74e8316c6eb4fdaa6598a46ce1d88af5",
3
+ "_name_or_path": "/home/ec2-user/.cache/huggingface/hub/models--riffusion--riffusion-model-v1/snapshots/8f2e752c74e8316c6eb4fdaa6598a46ce1d88af5/safety_checker",
4
+ "architectures": [
5
+ "StableDiffusionSafetyChecker"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "logit_scale_init_value": 2.6592,
9
+ "model_type": "clip",
10
+ "projection_dim": 768,
11
+ "text_config": {
12
+ "_name_or_path": "",
13
+ "add_cross_attention": false,
14
+ "architectures": null,
15
+ "attention_dropout": 0.0,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "dropout": 0.0,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 2,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "hidden_act": "quick_gelu",
33
+ "hidden_size": 768,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_factor": 1.0,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "is_decoder": false,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 77,
51
+ "min_length": 0,
52
+ "model_type": "clip_text_model",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 12,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 12,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 1,
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "projection_dim": 512,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "sep_token_id": null,
72
+ "suppress_tokens": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tf_legacy_loss": false,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": null,
82
+ "torchscript": false,
83
+ "transformers_version": "4.29.2",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
+ },
88
+ "torch_dtype": "float32",
89
+ "transformers_version": null,
90
+ "vision_config": {
91
+ "_name_or_path": "",
92
+ "add_cross_attention": false,
93
+ "architectures": null,
94
+ "attention_dropout": 0.0,
95
+ "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
+ "bos_token_id": null,
98
+ "chunk_size_feed_forward": 0,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "dropout": 0.0,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": null,
107
+ "exponential_decay_length_penalty": null,
108
+ "finetuning_task": null,
109
+ "forced_bos_token_id": null,
110
+ "forced_eos_token_id": null,
111
+ "hidden_act": "quick_gelu",
112
+ "hidden_size": 1024,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "image_size": 224,
118
+ "initializer_factor": 1.0,
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 4096,
121
+ "is_decoder": false,
122
+ "is_encoder_decoder": false,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1
126
+ },
127
+ "layer_norm_eps": 1e-05,
128
+ "length_penalty": 1.0,
129
+ "max_length": 20,
130
+ "min_length": 0,
131
+ "model_type": "clip_vision_model",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 16,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_channels": 3,
137
+ "num_hidden_layers": 24,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_scores": false,
142
+ "pad_token_id": null,
143
+ "patch_size": 14,
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "projection_dim": 512,
147
+ "pruned_heads": {},
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sep_token_id": null,
153
+ "suppress_tokens": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tf_legacy_loss": false,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": true,
159
+ "tokenizer_class": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": null,
163
+ "torchscript": false,
164
+ "transformers_version": "4.29.2",
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false
167
+ }
168
+ }
safety_checker/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
3
+ size 1216064769
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "num_train_timesteps": 1000,
8
+ "prediction_type": "epsilon",
9
+ "set_alpha_to_one": false,
10
+ "skip_prk_steps": true,
11
+ "steps_offset": 1,
12
+ "trained_betas": null
13
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "riffusion/riffusion-model-v1",
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": "float16",
23
+ "transformers_version": "4.29.2",
24
+ "vocab_size": 49408
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a34f30098988d85dc0fb0fc272a842ebcf552e2ebc6ce4adbcf3695d08e8a90
3
+ size 246188833