End of training

.gitignore

@@ -0,0 +1,3 @@
+step_*
+checkpoint-*
+checkpoint-*

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-cartoonizer/1711202127.285256/events.out.tfevents.1711202127.423eef49132e.1199.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb90a6e8252372df5aa5318f249adf1136d7c6a6cc349cee262e9ec5f599c46
+size 2585

logs/instruct-pix2pix-cartoonizer/1711202127.2871852/hparams.yml

@@ -0,0 +1,50 @@
+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: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: instruction-tuning-sd/cartoonization
+edit_prompt_column: edit_prompt
+edited_image_column: cartoonized_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: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 60
+num_validation_images: 4
+original_image_column: original_image
+output_dir: cartoonization-scratch-v2
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+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: 5
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+val_image_url: https://hf.co/datasets/diffusers/diffusers-images-docs/resolve/main/mountain.png
+validation_epochs: 1
+validation_prompt: Generate a cartoonized version of the natural image

logs/instruct-pix2pix-cartoonizer/1711202183.7766469/events.out.tfevents.1711202183.423eef49132e.2767.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812a59e980e40bb5007732b650abf01896e6614a78b22edc0eff6b0259046d32
+size 2585

logs/instruct-pix2pix-cartoonizer/1711202183.7784517/hparams.yml

@@ -0,0 +1,50 @@
+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: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: instruction-tuning-sd/cartoonization
+edit_prompt_column: edit_prompt
+edited_image_column: cartoonized_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: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 15000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 24
+num_validation_images: 4
+original_image_column: original_image
+output_dir: cartoonization-scratch-v2
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+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: 2
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+val_image_url: https://hf.co/datasets/diffusers/diffusers-images-docs/resolve/main/mountain.png
+validation_epochs: 1
+validation_prompt: Generate a cartoonized version of the natural image

logs/instruct-pix2pix-cartoonizer/1711202237.7999675/events.out.tfevents.1711202237.423eef49132e.3070.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5767c5bd0f2d79d015a46bda056f8717a6255e1cbce4066fb88805053eb1cc6
+size 2585

logs/instruct-pix2pix-cartoonizer/1711202237.8017662/hparams.yml

@@ -0,0 +1,50 @@
+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: 500
+checkpoints_total_limit: 1
+conditioning_dropout_prob: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: instruction-tuning-sd/cartoonization
+edit_prompt_column: edit_prompt
+edited_image_column: cartoonized_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: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 2000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 7
+num_validation_images: 4
+original_image_column: original_image
+output_dir: cartoonization-scratch-v2
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+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: true
+val_image_url: https://hf.co/datasets/diffusers/diffusers-images-docs/resolve/main/mountain.png
+validation_epochs: 1
+validation_prompt: Generate a cartoonized version of the natural image

logs/instruct-pix2pix-cartoonizer/1711202332.833262/events.out.tfevents.1711202332.423eef49132e.3547.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e02136ed6eaa9a0a0ec933ae3b6a7d0b81b19bd16d31eb56b6ed89dd8261935
+size 2585

logs/instruct-pix2pix-cartoonizer/1711202332.8350902/hparams.yml

@@ -0,0 +1,50 @@
+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: 500
+checkpoints_total_limit: 1
+conditioning_dropout_prob: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: instruction-tuning-sd/cartoonization
+edit_prompt_column: edit_prompt
+edited_image_column: cartoonized_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: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 3000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 10
+num_validation_images: 4
+original_image_column: original_image
+output_dir: cartoonization-scratch-v2
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+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: true
+val_image_url: https://hf.co/datasets/diffusers/diffusers-images-docs/resolve/main/mountain.png
+validation_epochs: 1
+validation_prompt: Generate a cartoonized version of the natural image

logs/instruct-pix2pix-cartoonizer/1711202401.638574/events.out.tfevents.1711202401.423eef49132e.3916.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd1bf82abd9d771f49a537832ce4d3d58d2e4431bb5d39dce4c911c2b6a265c
+size 2585

logs/instruct-pix2pix-cartoonizer/1711202401.6404674/hparams.yml

@@ -0,0 +1,50 @@
+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: 800
+checkpoints_total_limit: 1
+conditioning_dropout_prob: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: instruction-tuning-sd/cartoonization
+edit_prompt_column: edit_prompt
+edited_image_column: cartoonized_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: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 3200
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 11
+num_validation_images: 4
+original_image_column: original_image
+output_dir: cartoonization-scratch-v2
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+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: true
+val_image_url: https://hf.co/datasets/diffusers/diffusers-images-docs/resolve/main/mountain.png
+validation_epochs: 1
+validation_prompt: Generate a cartoonized version of the natural image

logs/instruct-pix2pix-cartoonizer/events.out.tfevents.1711202127.423eef49132e.1199.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d2be6c04ba545e83ae41e98308392c80f6a0952c5054291d679cd7457b0551
+size 616

logs/instruct-pix2pix-cartoonizer/events.out.tfevents.1711202183.423eef49132e.2767.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29c315d174d908e2377aba0ebafa2282ffda71565b5c2847019d3c0035b242f1
+size 424

logs/instruct-pix2pix-cartoonizer/events.out.tfevents.1711202237.423eef49132e.3070.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374c103da1cf3320ca299d72bccf4bdd0f5fcae0bbe76de29dc579aafdd2327b
+size 1672

logs/instruct-pix2pix-cartoonizer/events.out.tfevents.1711202332.423eef49132e.3547.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33dc19fc15d915e10e7f2657a40bb9f3861665e1eb366c19e5582d82c254358
+size 1144

logs/instruct-pix2pix-cartoonizer/events.out.tfevents.1711202401.423eef49132e.3916.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6e37c46ba410604d1f58877b66f2215cf2e5709c277367bcd9454b37aa1158
+size 156761

model_index.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "StableDiffusionInstructPix2PixPipeline",
+  "_diffusers_version": "0.27.2",
+  "_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 +1,28 @@
+{
+  "_name_or_path": "/root/.cache/huggingface/hub/models--timbrooks--instruct-pix2pix/snapshots/31519b5cb02a7fd89b906d88731cd4d6a7bbf88d/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": "4.38.2",
+  "vision_config": {
+    "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 +1,23 @@
+{
+  "_class_name": "EulerAncestralDiscreteScheduler",
+  "_diffusers_version": "0.27.2",
+  "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 +1,25 @@
+{
+  "_name_or_path": "timbrooks/instruct-pix2pix",
+  "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": "4.38.2",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

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

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.27.2",
+  "_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
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba7dbd3b0f4323ec507c9cbb1cb6a7c71078fe02637c4343b37d9a325a48f660
+size 3438213624

vae/config.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.27.2",
+  "_name_or_path": "timbrooks/instruct-pix2pix",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
+size 167335342