Hugging Face's logo

indu22
/
zach_retrain_1

Diffusers
TensorBoard
StableDiffusionInstructPix2PixPipeline
Model card Files Metrics Community
indu22 commited on
Commit
3cf5c51
•
1 Parent(s): 87deaf9

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. checkpoint-150000/optimizer.bin +3 -0
  2. checkpoint-150000/random_states_0.pkl +3 -0
  3. checkpoint-150000/scaler.pt +3 -0
  4. checkpoint-150000/scheduler.bin +3 -0
  5. checkpoint-150000/unet/config.json +65 -0
  6. checkpoint-150000/unet/diffusion_pytorch_model.bin +3 -0
  7. checkpoint-200000/optimizer.bin +3 -0
  8. checkpoint-200000/random_states_0.pkl +3 -0
  9. checkpoint-200000/scaler.pt +3 -0
  10. checkpoint-200000/scheduler.bin +3 -0
  11. checkpoint-200000/unet/config.json +65 -0
  12. checkpoint-200000/unet/diffusion_pytorch_model.bin +3 -0
  13. logs/instruct-pix2pix/1696913448.708236/events.out.tfevents.1696913448.ip-172-31-5-183.1152555.1 +3 -0
  14. logs/instruct-pix2pix/1696913448.7096176/hparams.yml +50 -0
  15. logs/instruct-pix2pix/1696927642.200138/events.out.tfevents.1696927642.ip-172-31-5-183.1350936.1 +3 -0
  16. logs/instruct-pix2pix/1696927642.2014725/hparams.yml +50 -0
  17. logs/instruct-pix2pix/events.out.tfevents.1696913448.ip-172-31-5-183.1152555.0 +3 -0
  18. logs/instruct-pix2pix/events.out.tfevents.1696927642.ip-172-31-5-183.1350936.0 +3 -0
checkpoint-150000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac27ed01585437473d3ba330a6b418bc8df93d7b4e0dc8f5ec11a483904a662f
3
+ size 6876841875
checkpoint-150000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a906d40c969c081a6c09aa26bbe8414eadcc88ad48aeedb37089a060afd2035
3
+ size 14599
checkpoint-150000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6513458be3ee9ff3b9b32eacfe45b52de57db4fac9fe55855d8404672bdd6b06
3
+ size 557
checkpoint-150000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3af772548c02ac5f228598f3a10f1ca344e633266799f75688ddbdd7a809b473
3
+ size 563
checkpoint-150000/unet/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.19.3",
4
+ "_name_or_path": "./data/pix2pix-riff-ckpt/checkpoint-120000",
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
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "center_input_sample": false,
17
+ "class_embed_type": null,
18
+ "class_embeddings_concat": false,
19
+ "conv_in_kernel": 3,
20
+ "conv_out_kernel": 3,
21
+ "cross_attention_dim": 768,
22
+ "cross_attention_norm": null,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "encoder_hid_dim": null,
32
+ "encoder_hid_dim_type": null,
33
+ "flip_sin_to_cos": true,
34
+ "freq_shift": 0,
35
+ "in_channels": 8,
36
+ "layers_per_block": 2,
37
+ "mid_block_only_cross_attention": null,
38
+ "mid_block_scale_factor": 1,
39
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
40
+ "norm_eps": 1e-05,
41
+ "norm_num_groups": 32,
42
+ "num_attention_heads": null,
43
+ "num_class_embeds": null,
44
+ "only_cross_attention": false,
45
+ "out_channels": 4,
46
+ "projection_class_embeddings_input_dim": null,
47
+ "resnet_out_scale_factor": 1.0,
48
+ "resnet_skip_time_act": false,
49
+ "resnet_time_scale_shift": "default",
50
+ "sample_size": 32,
51
+ "time_cond_proj_dim": null,
52
+ "time_embedding_act_fn": null,
53
+ "time_embedding_dim": null,
54
+ "time_embedding_type": "positional",
55
+ "timestep_post_act": null,
56
+ "transformer_layers_per_block": 1,
57
+ "up_block_types": [
58
+ "UpBlock2D",
59
+ "CrossAttnUpBlock2D",
60
+ "CrossAttnUpBlock2D",
61
+ "CrossAttnUpBlock2D"
62
+ ],
63
+ "upcast_attention": false,
64
+ "use_linear_projection": false
65
+ }
checkpoint-150000/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d9c1d0eb50a32759764b0256718fe60779f785968bfbacf4a83ac992d0a6816
3
+ size 3438422053
checkpoint-200000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:446a9483fe4f6502c295719ee897c60f62889a65cf60ef19f86c4c74e4493c48
3
+ size 6876841875
checkpoint-200000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a164f186a462589c3947066659bf680f7b543b5ab8146e1e9d9d7fd67de4960e
3
+ size 14599
checkpoint-200000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cd286a1434d55a2bafbdfe03553cfa24aa4018115e37dab762079930814ba8a
3
+ size 557
checkpoint-200000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:299d63f15657732e2644484bc7b4347f11ab125316a097b1e5aa60232566805f
3
+ size 563
checkpoint-200000/unet/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.19.3",
4
+ "_name_or_path": "./data/pix2pix-riff-ckpt/checkpoint-150000",
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
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "center_input_sample": false,
17
+ "class_embed_type": null,
18
+ "class_embeddings_concat": false,
19
+ "conv_in_kernel": 3,
20
+ "conv_out_kernel": 3,
21
+ "cross_attention_dim": 768,
22
+ "cross_attention_norm": null,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "encoder_hid_dim": null,
32
+ "encoder_hid_dim_type": null,
33
+ "flip_sin_to_cos": true,
34
+ "freq_shift": 0,
35
+ "in_channels": 8,
36
+ "layers_per_block": 2,
37
+ "mid_block_only_cross_attention": null,
38
+ "mid_block_scale_factor": 1,
39
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
40
+ "norm_eps": 1e-05,
41
+ "norm_num_groups": 32,
42
+ "num_attention_heads": null,
43
+ "num_class_embeds": null,
44
+ "only_cross_attention": false,
45
+ "out_channels": 4,
46
+ "projection_class_embeddings_input_dim": null,
47
+ "resnet_out_scale_factor": 1.0,
48
+ "resnet_skip_time_act": false,
49
+ "resnet_time_scale_shift": "default",
50
+ "sample_size": 32,
51
+ "time_cond_proj_dim": null,
52
+ "time_embedding_act_fn": null,
53
+ "time_embedding_dim": null,
54
+ "time_embedding_type": "positional",
55
+ "timestep_post_act": null,
56
+ "transformer_layers_per_block": 1,
57
+ "up_block_types": [
58
+ "UpBlock2D",
59
+ "CrossAttnUpBlock2D",
60
+ "CrossAttnUpBlock2D",
61
+ "CrossAttnUpBlock2D"
62
+ ],
63
+ "upcast_attention": false,
64
+ "use_linear_projection": false
65
+ }
checkpoint-200000/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c301a121afa20cdedfb87e8e3259548dbdc6c6039b26bdf2f3baba38936c2f99
3
+ size 3438422053
logs/instruct-pix2pix/1696913448.708236/events.out.tfevents.1696913448.ip-172-31-5-183.1152555.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2144ec5f7d9bd60c684fd24350305d0c42aba5ecebceae545ac6cfa26d58934c
3
+ size 2446
logs/instruct-pix2pix/1696913448.7096176/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: 1.0e-05
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: 256
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/1696927642.200138/events.out.tfevents.1696927642.ip-172-31-5-183.1350936.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a03b7b8c17bc51cc435e64eb46768cb356971a58446f4df86a975780fafbda4
3
+ size 2446
logs/instruct-pix2pix/1696927642.2014725/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: 50000
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: 1.0e-05
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: 256
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.1696913448.ip-172-31-5-183.1152555.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e3661dcd5550d0c5ac4c89ff429481fc2423dbf25861579679eecac0c313a7
3
+ size 1536088
logs/instruct-pix2pix/events.out.tfevents.1696927642.ip-172-31-5-183.1350936.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1a8046cb4d2ac872fbf9d2d5bf700213554f08ab85f2d56689cb31b3df3a05b
3
+ size 2820738