Hugging Face's logo

serjsaraev
/
instruct-pix2pix-model

Diffusers
TensorBoard
Safetensors
StableDiffusionXLInstructPix2PixPipeline
Model card Files Metrics Community
serjsaraev commited on
Commit
1d873a9
·
verified ·
1 Parent(s): a41c5c9

End of training

Browse files
Files changed (17) hide show
  1. checkpoint-1000/optimizer.bin +3 -0
  2. checkpoint-1000/random_states_0.pkl +3 -0
  3. checkpoint-1000/scaler.pt +3 -0
  4. checkpoint-1000/scheduler.bin +3 -0
  5. checkpoint-1000/unet/config.json +73 -0
  6. checkpoint-1000/unet/diffusion_pytorch_model.safetensors +3 -0
  7. checkpoint-900/optimizer.bin +3 -0
  8. checkpoint-900/random_states_0.pkl +3 -0
  9. checkpoint-900/scaler.pt +3 -0
  10. checkpoint-900/scheduler.bin +3 -0
  11. checkpoint-900/unet/config.json +73 -0
  12. checkpoint-900/unet/diffusion_pytorch_model.safetensors +3 -0
  13. logs/instruct-pix2pix-xl/1717705168.9203477/events.out.tfevents.1717705168.ares.415877.1 +3 -0
  14. logs/instruct-pix2pix-xl/1717705168.9217377/hparams.yml +55 -0
  15. logs/instruct-pix2pix-xl/events.out.tfevents.1717705168.ares.415877.0 +3 -0
  16. unet/config.json +1 -1
  17. unet/diffusion_pytorch_model.safetensors +1 -1
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10bc1627e59745b5ac89225119b46be2203d7ff52340a6649eb875897b36b4cc
3
+ size 20541266058
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1453b41faed5a99ff4879a842cd61aae914c8b09a261abb5f3206bfda4207469
3
+ size 14604
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8fdcd0311eba9854fff738038ed4c1a269832665b4d88ba4e4e3d02a1a7e0e
3
+ size 988
checkpoint-1000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc9d529863b9458dbb9b91d10c2e89741ffa38f99dbc44be25770289ed29416
3
+ size 1000
checkpoint-1000/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280
19
+ ],
20
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 8,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "reverse_transformer_layers_per_block": null,
55
+ "sample_size": 128,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": [
62
+ 1,
63
+ 2,
64
+ 10
65
+ ],
66
+ "up_block_types": [
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "UpBlock2D"
70
+ ],
71
+ "upcast_attention": null,
72
+ "use_linear_projection": true
73
+ }
checkpoint-1000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e68bf5a09616addb7d035ba01354792f7c3eb089bc1b91ae00d8dae7552a17
3
+ size 10270123816
checkpoint-900/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e80b72d86df36f5d167fec84e3e5a148212a30c1a49e15e91432c6531633bcb
3
+ size 20541266058
checkpoint-900/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93d6666bce99269cf7f9d001a61895689d1b19f74afc5457114440fae985383d
3
+ size 14604
checkpoint-900/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3188ca1a64b3e854c359f175f9debb352690ec074d6533bcb271fdc5844d8a34
3
+ size 988
checkpoint-900/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90c19c63208c4d9999ca8b52a8f2141c903cf3531dd694250943d19bdfe80b74
3
+ size 1000
checkpoint-900/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280
19
+ ],
20
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 8,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "reverse_transformer_layers_per_block": null,
55
+ "sample_size": 128,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": [
62
+ 1,
63
+ 2,
64
+ 10
65
+ ],
66
+ "up_block_types": [
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "UpBlock2D"
70
+ ],
71
+ "upcast_attention": null,
72
+ "use_linear_projection": true
73
+ }
checkpoint-900/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c326ff631dff96a064908446af935370ffe22f199c7a28e9b8cd5ae93785d9e3
3
+ size 10270123816
logs/instruct-pix2pix-xl/1717705168.9203477/events.out.tfevents.1717705168.ares.415877.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e3d96d5935a05587ac215b7dfbfc504ab71023f531966ef376c2d64861294c
3
+ size 2564
logs/instruct-pix2pix-xl/1717705168.9217377/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ crops_coords_top_left_h: 0
12
+ crops_coords_top_left_w: 0
13
+ dataloader_num_workers: 0
14
+ dataset_config_name: null
15
+ dataset_name: /home/ssaraev/data/merge.dataset
16
+ edit_prompt_column: edit_prompt
17
+ edited_image_column: edited_image
18
+ enable_xformers_memory_efficient_attention: true
19
+ gradient_accumulation_steps: 4
20
+ gradient_checkpointing: true
21
+ hub_model_id: null
22
+ hub_token: null
23
+ learning_rate: 1.0e-06
24
+ local_rank: 0
25
+ logging_dir: logs
26
+ lr_scheduler: constant
27
+ lr_warmup_steps: 0
28
+ max_grad_norm: 1.0
29
+ max_train_samples: null
30
+ max_train_steps: 1000
31
+ mixed_precision: null
32
+ non_ema_revision: null
33
+ num_train_epochs: 1
34
+ num_validation_images: 4
35
+ original_image_column: input_image
36
+ output_dir: instruct-pix2pix-model
37
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
38
+ pretrained_vae_model_name_or_path: null
39
+ push_to_hub: true
40
+ random_flip: false
41
+ report_to: tensorboard
42
+ resolution: 1024
43
+ resume_from_checkpoint: null
44
+ revision: null
45
+ scale_lr: false
46
+ seed: 42
47
+ train_batch_size: 4
48
+ train_data_dir: null
49
+ use_8bit_adam: false
50
+ use_ema: false
51
+ vae_precision: fp32
52
+ val_image_url_or_path: null
53
+ validation_prompt: null
54
+ validation_steps: 100
55
+ variant: null
logs/instruct-pix2pix-xl/events.out.tfevents.1717705168.ares.415877.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:430277af5d57cc34c142cf0e0287a0d1218d8578630593a17cdbd3f58efe62bb
3
+ size 48961
unet/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.29.0.dev0",
4
- "_name_or_path": "instruct-pix2pix-model/checkpoint-5000",
5
  "act_fn": "silu",
6
  "addition_embed_type": "text_time",
7
  "addition_embed_type_num_heads": 64,
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
  "act_fn": "silu",
6
  "addition_embed_type": "text_time",
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 sha256:5187aebeb381dd248a8caf7e75d678e85fa8199ee551af553592a3d51a0580be
3
  size 10270123816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e68bf5a09616addb7d035ba01354792f7c3eb089bc1b91ae00d8dae7552a17
3
  size 10270123816