End of training

checkpoint-2000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:653ca0da7703597e7a8fe2625b5e000c3d5e7621b7e42c4f8d870f78360fc919
+size 6876842324

checkpoint-2000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd0ab3e9ef9727e0aabeb812322305193e784c835dc257aba348affa6fe3cec
+size 14408

checkpoint-2000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c50a9cebe5d66d453d25b140738bff479749ac03e0a43597d8776bc22f6ed0c
+size 988

checkpoint-2000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a65898fd80ad1f5b3504355ba22c7c0f5854b105b47e4ad00c9a7a016fda2229
+size 1000

checkpoint-2000/unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 8,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

checkpoint-2000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89095b273ee97b7d221ba2af430054e3a006f682951998a765b9e58be5f15843
+size 3438213624

feature_extractor/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

logs/instruct-pix2pix-xl/1739017328.9015243/events.out.tfevents.1739017328.spcc-a40g02.1673616.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f421ea09d36030d68066fb376f9ac38a5dc42b1456e64021834646d2057d1c99
+size 2567

logs/instruct-pix2pix-xl/1739017328.908869/hparams.yml

@@ -0,0 +1,55 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: fusing/instructpix2pix-1000-samples
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 239
+num_validation_images: 4
+original_image_column: input_image
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+pretrained_vae_model_name_or_path: null
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 256
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+vae_precision: fp32
+val_image_url_or_path: null
+validation_prompt: null
+validation_steps: 100
+variant: null

logs/instruct-pix2pix-xl/1739017900.7121582/events.out.tfevents.1739017900.spcc-a40g02.1677303.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc9caa8704728c7ec23d670ac55ebbf41bbc1125eda86203a2cee27f4d73ceba
+size 2567

logs/instruct-pix2pix-xl/1739017900.7204247/hparams.yml

@@ -0,0 +1,55 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: fusing/instructpix2pix-1000-samples
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 239
+num_validation_images: 4
+original_image_column: input_image
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+pretrained_vae_model_name_or_path: null
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 256
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+vae_precision: fp32
+val_image_url_or_path: null
+validation_prompt: null
+validation_steps: 100
+variant: null

logs/instruct-pix2pix-xl/1739024788.2772908/events.out.tfevents.1739024788.spcc-a40g14.445920.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e618064a2afb25eb040379c7463ae72ba0d9671c4e4374878c58aae712d580a
+size 2567

logs/instruct-pix2pix-xl/1739024788.2843132/hparams.yml

@@ -0,0 +1,55 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+crops_coords_top_left_h: 0
+crops_coords_top_left_w: 0
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: fusing/instructpix2pix-1000-samples
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 239
+num_validation_images: 4
+original_image_column: input_image
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+pretrained_vae_model_name_or_path: null
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 256
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+vae_precision: fp32
+val_image_url_or_path: null
+validation_prompt: null
+validation_steps: 100
+variant: null

logs/instruct-pix2pix-xl/events.out.tfevents.1739017328.spcc-a40g02.1673616.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442edece3d668ec32b25e01c3dd316193e81890966e036495414602af1a97871
+size 88

logs/instruct-pix2pix-xl/events.out.tfevents.1739017900.spcc-a40g02.1677303.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:387b386dde56fef0ac2e02f07547413c8f1ae71555051239be76bf21fe65f19b
+size 88

logs/instruct-pix2pix-xl/events.out.tfevents.1739024788.spcc-a40g14.445920.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc8cd16a6f280ae3911d593f62175bd255900b6763008c47210e96ff15b06d4
+size 88

logs/instruct-pix2pix/1739018978.779651/events.out.tfevents.1739018978.spcc-a40g19.1239308.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49b6730993cc232fffd6e7e4ce5cb487203586e3d49bb3f1e4c8c598672e4911
+size 2445

logs/instruct-pix2pix/1739018978.7848387/hparams.yml

@@ -0,0 +1,51 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: sayakpaul/instructpix2pix-1000-samples
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: 0
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 469
+num_validation_images: 4
+original_image_column: input_image
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null
+variant: null

logs/instruct-pix2pix/1739025279.2984846/events.out.tfevents.1739025279.spcc-a40g14.448688.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9effbc527dc0148cdbca64ea37bbea7b98c5ae55ccc2880913cc97ea594a8d
+size 2442

logs/instruct-pix2pix/1739025279.304702/hparams.yml

@@ -0,0 +1,51 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: fusing/instructpix2pix-1000-samples
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 239
+num_validation_images: 4
+original_image_column: input_image
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 256
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null
+variant: null

logs/instruct-pix2pix/1739029644.28327/events.out.tfevents.1739029644.spcc-a40g14.472330.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f40e83ed68304ca0bfcc9f900d6105197a5a060409bd312369fadc91bf615b0
+size 2448

logs/instruct-pix2pix/1739029644.2910244/hparams.yml

@@ -0,0 +1,51 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+edit_prompt_column: instruction
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 334
+num_validation_images: 4
+original_image_column: image_name
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 256
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: ./self_barefoot_dataset/new_structure/
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null
+variant: null

logs/instruct-pix2pix/1739029905.340061/events.out.tfevents.1739029905.spcc-a40g14.473747.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcacb0cc69f57f5c8b24f4a4a19d1a42cd30cdd0aa205e589897940630a1332a
+size 2448

logs/instruct-pix2pix/1739029905.3451133/hparams.yml

@@ -0,0 +1,51 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+edit_prompt_column: instruction
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 334
+num_validation_images: 4
+original_image_column: image_name
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 256
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: ./self_barefoot_dataset/new_structure/
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null
+variant: null

logs/instruct-pix2pix/1739030361.8407564/events.out.tfevents.1739030361.spcc-a40g14.476260.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399871eec6d60ea99518284915baa76bf67c35aee8097f1314bdd71e05009bc7
+size 2448

logs/instruct-pix2pix/1739030361.8500128/hparams.yml

@@ -0,0 +1,51 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+edit_prompt_column: instruction
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 334
+num_validation_images: 4
+original_image_column: image_name
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 256
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: ./self_barefoot_dataset/new_structure/
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null
+variant: null

logs/instruct-pix2pix/1739030438.2365324/events.out.tfevents.1739030438.spcc-a40g14.476772.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4697b4e75b92abc69809bd2f2de0ad6eca8a9ff1503a631d51684d88754777fd
+size 2448

logs/instruct-pix2pix/1739030438.2423885/hparams.yml

@@ -0,0 +1,51 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+edit_prompt_column: instruction
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 334
+num_validation_images: 4
+original_image_column: image_name
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 256
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: ./self_barefoot_dataset/new_structure/
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null
+variant: null

logs/instruct-pix2pix/1739030577.7740219/events.out.tfevents.1739030577.spcc-a40g14.477553.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76c027ead7f9fcef951dbf888ba2bb5e98db0fae2e53b440eff4096f9f407c0a
+size 2448

logs/instruct-pix2pix/1739030577.7788777/hparams.yml

@@ -0,0 +1,51 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+edit_prompt_column: instruction
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 8
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1250
+num_validation_images: 4
+original_image_column: image_name
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 8
+train_data_dir: ./self_barefoot_dataset/new_structure/
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null
+variant: null

logs/instruct-pix2pix/1739030713.9233325/events.out.tfevents.1739030713.spcc-a40g14.478386.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a65cc0b1215bbe69414fe9d6dcd457397014910f77b372f3aa25056cfc0b22d5
+size 2448

logs/instruct-pix2pix/1739030713.9285104/hparams.yml

@@ -0,0 +1,51 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 5000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+edit_prompt_column: instruction
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 334
+num_validation_images: 4
+original_image_column: image_name
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: ./self_barefoot_dataset/new_structure/
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null
+variant: null

logs/instruct-pix2pix/1739031020.4435735/events.out.tfevents.1739031020.spcc-a40g14.479886.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa420538c6ba01e8efa22c164ba0f39db04d1bb1ec1d50e9dae5bf41f03a788c
+size 2448

logs/instruct-pix2pix/1739031020.4503279/hparams.yml

@@ -0,0 +1,51 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 200
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+edit_prompt_column: instruction
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 2000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 45
+num_validation_images: 4
+original_image_column: image_name
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: ./self_barefoot_dataset/new_structure/
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null
+variant: null

logs/instruct-pix2pix/events.out.tfevents.1739018978.spcc-a40g19.1239308.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a8ad11fc7d627e19a6eb9a1091869cfbbb3f7f37ec881ea8ee9fb34aae272c
+size 94972

logs/instruct-pix2pix/events.out.tfevents.1739025279.spcc-a40g14.448688.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9800322290748eaba5160857753d8c3c75324c8a0f7dfe2fbc2cbf70bdbbd106
+size 60280

logs/instruct-pix2pix/events.out.tfevents.1739029644.spcc-a40g14.472330.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e020f087b1eee95833bb81bd730049535bd6c2714aa1cbd98c750fe25ce7b25
+size 88

logs/instruct-pix2pix/events.out.tfevents.1739029905.spcc-a40g14.473747.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64cd014b5f2d71a2642f6a5f50c73fcdb483282bd2164e9a769007e55141fefa
+size 88

logs/instruct-pix2pix/events.out.tfevents.1739030361.spcc-a40g14.476260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f91bd85c24885fb553c96193a5743bf72d0dfd95514a401f6712032936f1de0e
+size 88

logs/instruct-pix2pix/events.out.tfevents.1739030438.spcc-a40g14.476772.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75268b871a0e971dc50d05b0719b44c9eb795754c9c7132b9d2eb53e35b21cbd
+size 664

logs/instruct-pix2pix/events.out.tfevents.1739030577.spcc-a40g14.477553.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:556fba99bd22505e524f8cea8bbe197d2fea50fdff78d665fc053032b59765f7
+size 232

logs/instruct-pix2pix/events.out.tfevents.1739030713.spcc-a40g14.478386.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a8a9b49e5eb9763cf9fde7a212ed09f834add74cf00f178f8942fb27472406
+size 856

logs/instruct-pix2pix/events.out.tfevents.1739031020.spcc-a40g14.479886.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f5509d1c16d2ea919f835d11abc65971825aae13ca515e5022a8a9c08d6ea0
+size 97961

model_index.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "StableDiffusionInstructPix2PixPipeline",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

safety_checker/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "./my_huggingface_cache/hub/models--stable-diffusion-v1-5--stable-diffusion-v1-5/snapshots/451f4fe16113bff5a5d2269ed5ad43b0592e9a14/safety_checker",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "dropout": 0.0,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
+  }
+}

safety_checker/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
+size 1215979664

scheduler/scheduler_config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.33.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.3",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+size 246144152