End of training

checkpoint-1000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e78d0844c422a0404444ef4848ed36f83eddd018130d571a4f48cdb8ce7329
+size 6876842324

checkpoint-1000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030f590484d5e72364759fc18832e5caff073c7ae0c071dec66284ff965cd7f9
+size 16100

checkpoint-1000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d8fdcd0311eba9854fff738038ed4c1a269832665b4d88ba4e4e3d02a1a7e0e
+size 988

checkpoint-1000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d16ae9dedf4c45ceadc467593037d83423677715e75ab402a9f44aa81de9b84
+size 1000

checkpoint-1000/unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.34.0.dev0",
+  "_name_or_path": "timbrooks/instruct-pix2pix",
+  "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-1000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e5c65e6affc479dfe006024306e169d820fbd14f068a0f50bb9201dc4769da
+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/1744991822.9506016/events.out.tfevents.1744991822.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.2303.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea84d75e52fa234ff7f38d394f75eeda0240f7077ab0e8b360bd14b430f6910
+size 2418

logs/instruct-pix2pix/1744991822.9843452/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: 25
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: youlive789/instructpix2pix
+edit_prompt_column: edit_promt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: true
+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: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: original_image
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+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: 2
+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/1745051623.3535006/events.out.tfevents.1745051623.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.2908.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf144d01d471abef647b412e6d37023cc07b232f4a8f8785cb7a532cffb236e
+size 2400

logs/instruct-pix2pix/1745051623.3786075/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: 25
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Aurora1609/Pix2Pix_RoboTwin
+edit_prompt_column: prompt
+edited_image_column: after
+enable_xformers_memory_efficient_attention: true
+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: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: before
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+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: 1
+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/1745051880.0799575/events.out.tfevents.1745051880.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3058.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72c4b5007ad8e45f1a0b4995e7fe32d4fb5c317bedeb4a2b4d657a62777172d
+size 2400

logs/instruct-pix2pix/1745051880.1131375/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: 25
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Aurora1609/Pix2Pix_RoboTwin
+edit_prompt_column: prompt
+edited_image_column: after
+enable_xformers_memory_efficient_attention: true
+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: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: before
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+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: 1
+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/1745051978.1224022/events.out.tfevents.1745051978.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3208.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab9cb4d1544674a8ad6d91b4520ec2193eb9cec434ebe43558e72f334ddaab9
+size 2400

logs/instruct-pix2pix/1745051978.149768/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: 25
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Aurora1609/Pix2Pix_RoboTwin
+edit_prompt_column: prompt
+edited_image_column: after
+enable_xformers_memory_efficient_attention: true
+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: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: before
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+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: 1
+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/1745052698.949806/events.out.tfevents.1745052698.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3358.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4ddb14a88de5cbb5128556978eec82784f37279263faff88c480115e46ac7d
+size 2400

logs/instruct-pix2pix/1745052698.9776397/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: 25
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Aurora1609/Pix2Pix_RoboTwin
+edit_prompt_column: prompt
+edited_image_column: after
+enable_xformers_memory_efficient_attention: true
+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: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: before
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+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: 1
+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/1745052760.7454703/events.out.tfevents.1745052760.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3508.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad92d3a21b861f847ddea8957d7f1db84bcdf16b8a76c5eaed4fb0e51bbb9c0a
+size 2400

logs/instruct-pix2pix/1745052760.7726707/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: 25
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Aurora1609/Pix2Pix_RoboTwin
+edit_prompt_column: prompt
+edited_image_column: after
+enable_xformers_memory_efficient_attention: true
+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: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: before
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 128
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 1
+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/1745053073.8717396/events.out.tfevents.1745053073.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3658.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5722ed54c98e7df3891fe7c3f89defeb6431fffad0a69e4b6cb092209416135
+size 2400

logs/instruct-pix2pix/1745053073.8990517/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: 25
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Aurora1609/Pix2Pix_RoboTwin
+edit_prompt_column: prompt
+edited_image_column: after
+enable_xformers_memory_efficient_attention: true
+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: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: before
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 128
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 1
+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/1745053235.5696728/events.out.tfevents.1745053235.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3808.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f141795bd9cabf366581fc205681a92de1079192b43817a12eaa2ceffb008b
+size 2400

logs/instruct-pix2pix/1745053235.59478/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: 25
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Aurora1609/Pix2Pix_RoboTwin
+edit_prompt_column: prompt
+edited_image_column: after
+enable_xformers_memory_efficient_attention: true
+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: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: before
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 128
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 1
+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/1745053296.8217793/events.out.tfevents.1745053296.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3958.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000efa8998899db04e842e2087410f72478c972be099fcdb46d9650ff0c870ad
+size 2400

logs/instruct-pix2pix/1745053296.8500984/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: 25
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Aurora1609/Pix2Pix_RoboTwin
+edit_prompt_column: prompt
+edited_image_column: after
+enable_xformers_memory_efficient_attention: true
+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: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: before
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 128
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 1
+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/1745496150.8769064/events.out.tfevents.1745496150.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-2s70vh-worker.2059.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc5eb5b562efe1e91046970d138acce562a470db183741f91a3e08ac87aa2e6
+size 2392

logs/instruct-pix2pix/1745496150.9082656/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: 25
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Aurora1609/RoboTwin
+edit_prompt_column: prompt
+edited_image_column: after
+enable_xformers_memory_efficient_attention: true
+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: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: before
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 128
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 1
+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/1745502128.123976/events.out.tfevents.1745502128.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-2s70vh-worker.2776.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f235b325a9829a381a0b7625f6f907765f10f7d04f090f030450d2d763d9d93
+size 2392

logs/instruct-pix2pix/1745502128.1537488/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: 25
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Aurora1609/RoboTwin
+edit_prompt_column: prompt
+edited_image_column: after
+enable_xformers_memory_efficient_attention: true
+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: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 1000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: before
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 128
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 1
+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/1745502541.4668396/events.out.tfevents.1745502541.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-2s70vh-worker.2998.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80b733a79ff47dd9686cc2c49927d85d00d7cbc14fc32af3657f9d258ad12cd
+size 2392

logs/instruct-pix2pix/1745502541.4967284/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: 25
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Aurora1609/RoboTwin
+edit_prompt_column: prompt
+edited_image_column: after
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 1.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 1000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: before
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 128
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 1
+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/events.out.tfevents.1744991822.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.2303.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65e397b8caadf48216cd6d33d6766165497f79684ac80721259fc896c4c11230
+size 4888

logs/instruct-pix2pix/events.out.tfevents.1745051623.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.2908.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c55f4d344c15ee50ce79d75c9905248fee514491f211397ef8d882810f7f4a
+size 88

logs/instruct-pix2pix/events.out.tfevents.1745051880.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3058.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732f2383b44c2c58c77b7431e46c93c7fdc7be0b6be378c107c6ab359a5848a2
+size 88

logs/instruct-pix2pix/events.out.tfevents.1745051978.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3208.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85b7be0e8c86327a3e0636d628dee637b7fd0ccf65038959cef962242c7b56a
+size 88

logs/instruct-pix2pix/events.out.tfevents.1745052698.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3358.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ef416fe5c0de38224619176066a32f49909cff1f80034a34a9daf035c9139d
+size 88

logs/instruct-pix2pix/events.out.tfevents.1745052760.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3508.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3348f03f1bda03c611f9e50d7a7419463b0d70e4c34d7801a97e0f0b7cc0f7e7
+size 88

logs/instruct-pix2pix/events.out.tfevents.1745053073.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3658.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3749eebdbfad215b5d2849fe2d37d1b3f5b189be053d1230c76aa528046b18b
+size 88

logs/instruct-pix2pix/events.out.tfevents.1745053235.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3808.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ce63cf974f7ed5bce7b2fca9ba2c195381cdf7c10584e41851488cda9e1f94
+size 88

logs/instruct-pix2pix/events.out.tfevents.1745053296.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-p403wp-worker.3958.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b19b6e5e2f9cd9a2154fb39322c57f337b8eb1a58016809accb7f0ea1454395
+size 4888

logs/instruct-pix2pix/events.out.tfevents.1745496150.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-2s70vh-worker.2059.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b71dea0774f1b9a081e5368ee8c2033cf58e69119034755d4d9c1b024cb17ebc
+size 4888

logs/instruct-pix2pix/events.out.tfevents.1745502128.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-2s70vh-worker.2776.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61353990d458260e4a2e6f8568b741cc8171bfa47694284cf98de70fc93647ce
+size 6674

logs/instruct-pix2pix/events.out.tfevents.1745502541.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-2s70vh-worker.2998.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3ab44c8ba9bfc255b698c2ea89a6755473f0d9be5b2b9eb91efd36fbc8819d
+size 48961

model_index.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "StableDiffusionInstructPix2PixPipeline",
+  "_diffusers_version": "0.34.0.dev0",
+  "_name_or_path": "timbrooks/instruct-pix2pix",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerAncestralDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

safety_checker/config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "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,
+    "projection_dim": 512,
+    "torch_dtype": "float32",
+    "vocab_size": 49408
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 512,
+    "torch_dtype": "float32"
+  }
+}

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 +1,23 @@
+{
+  "_class_name": "EulerAncestralDiscreteScheduler",
+  "_diffusers_version": "0.34.0.dev0",
+  "algorithm_type": "dpmsolver++",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "dynamic_thresholding_ratio": 0.995,
+  "lower_order_final": true,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "solver_order": 2,
+  "solver_type": "midpoint",
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "linspace",
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "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": "4.51.3",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

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