End of training

checkpoint-4000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaf02e45441710b4120f051974c378e280a5c0041c51e0c1baf17e053c1db72a
+size 6876841875

checkpoint-4000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01348462a49896114c1aa292d013366d5cf9cc895be3f4152607c6498eec1f06
+size 14663

checkpoint-4000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09a61ecdaa4a69ba865e0b9e19169660549c34c60a83537ab5ece413678520ab
+size 557

checkpoint-4000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e799c66721855ee832d69fa6c72f957c8e84ab8272c5aca107dac61118a229e
+size 563

checkpoint-4000/unet/config.json

@@ -0,0 +1,67 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.22.0.dev0",
+  "_name_or_path": "/scratch/ssd004/scratch/rishit/diffusion-isp-model-new/checkpoint-3500",
+  "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",
+  "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-4000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3177f2add7002d1c7692218e308940bb49f3c7617773826337c9cb581354b6
+size 3438213624

checkpoint-4000/unet_ema/config.json

@@ -0,0 +1,74 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.22.0.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,
+  "decay": 0.9999,
+  "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,
+  "inv_gamma": 1.0,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "min_decay": 0.0,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "optimization_step": 500,
+  "out_channels": 4,
+  "power": 0.6666666666666666,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "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,
+  "update_after_step": 0,
+  "use_ema_warmup": false,
+  "use_linear_projection": false
+}

checkpoint-4000/unet_ema/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f09a76479ed684c97538bf5d233edd477b6ecdd2c9f51681cf44593bce186c3
+size 3438213624

feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "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/diffusion-isp/1696829881.5769048/events.out.tfevents.1696829881.gpu011.4219.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ec073dbc47e72654f86f0d05916b5e601779005d18732c693d9289e34021af
+size 2529

logs/diffusion-isp/1696829881.584409/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: /scratch/ssd004/scratch/rishit/train_cache
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: 2
+conditioning_dropout_prob: 0.003
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: rishitdagli/diffusion-isp-low-light-only
+edit_prompt_column: prompt
+edited_image_column: ground_truth
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 0.0001
+local_rank: 0
+logging_dir: logs
+lr_scheduler: cosine
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 35100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 300
+num_validation_images: 4
+original_image_column: input_image
+output_dir: /scratch/ssd004/scratch/rishit/diffusion-isp-model-new
+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: 3407
+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

logs/diffusion-isp/1696883562.274425/events.out.tfevents.1696883562.gpu047.7817.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8207ab47a237047b694bea01798ca25174164e856cc96cae9d8c90814406bc
+size 2593

logs/diffusion-isp/1696883562.282633/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: /scratch/ssd004/scratch/rishit/train_cache
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.003
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: rishitdagli/diffusion-isp-low-light-only
+edit_prompt_column: prompt
+edited_image_column: ground_truth
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 0.0001
+local_rank: 0
+logging_dir: logs
+lr_scheduler: cosine
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 35100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 300
+num_validation_images: 4
+original_image_column: input_image
+output_dir: /scratch/ssd004/scratch/rishit/diffusion-isp-model-new
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: 3407
+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

logs/diffusion-isp/1696952816.7710686/events.out.tfevents.1696952816.gpu038.31999.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76c59bc1a9851adf9b8b0cbfeb6b86f107fb0e51f810aade7b358a9d4a9b6e47
+size 2593

logs/diffusion-isp/1696952816.777575/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: /scratch/ssd004/scratch/rishit/train_cache
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.003
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: rishitdagli/diffusion-isp-low-light-only
+edit_prompt_column: prompt
+edited_image_column: ground_truth
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 0.0001
+local_rank: 0
+logging_dir: logs
+lr_scheduler: cosine
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 35100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 300
+num_validation_images: 4
+original_image_column: input_image
+output_dir: /scratch/ssd004/scratch/rishit/diffusion-isp-model-new
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: 3407
+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

logs/diffusion-isp/1696977884.3538234/events.out.tfevents.1696977884.gpu008.22282.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a804bc650b7477e24f861c04f72ab96d4ba65799e602b3594e17e6ee20c81b1a
+size 2593

logs/diffusion-isp/1696977884.3622146/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: /scratch/ssd004/scratch/rishit/train_cache
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.003
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: rishitdagli/diffusion-isp-low-light-only
+edit_prompt_column: prompt
+edited_image_column: ground_truth
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 0.0001
+local_rank: 0
+logging_dir: logs
+lr_scheduler: cosine
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 35100
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 300
+num_validation_images: 4
+original_image_column: input_image
+output_dir: /scratch/ssd004/scratch/rishit/diffusion-isp-model-new
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: 3407
+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

logs/diffusion-isp/1696979969.4608314/events.out.tfevents.1696979969.gpu008.22612.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5455d8fccfb053d43e1f2d8a746bedeb5f02a1940ed38623921001d229c7ecb9
+size 2593

logs/diffusion-isp/1696979969.4689977/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: /scratch/ssd004/scratch/rishit/train_cache
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.003
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: rishitdagli/diffusion-isp-low-light-only
+edit_prompt_column: prompt
+edited_image_column: ground_truth
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 0.0001
+local_rank: 0
+logging_dir: logs
+lr_scheduler: cosine
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 11700
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 100
+num_validation_images: 4
+original_image_column: input_image
+output_dir: /scratch/ssd004/scratch/rishit/diffusion-isp-model-new
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: 3407
+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

logs/diffusion-isp/1696982383.99139/events.out.tfevents.1696982383.gpu048.32362.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:560ee1f764dd59f9b7204675a20ed60b27ff2d8297f5849213dd84faab38ebcf
+size 2593

logs/diffusion-isp/1696982383.998017/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: /scratch/ssd004/scratch/rishit/train_cache
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.003
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: rishitdagli/diffusion-isp-low-light-only
+edit_prompt_column: prompt
+edited_image_column: ground_truth
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 0.0001
+local_rank: 0
+logging_dir: logs
+lr_scheduler: cosine
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 117
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+original_image_column: input_image
+output_dir: /scratch/ssd004/scratch/rishit/diffusion-isp-model-new
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: 3407
+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

logs/diffusion-isp/events.out.tfevents.1696829881.gpu011.4219.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638963c7037932b26c0356f2b886bd34de916c63eb3fda21ac3c9e8d244b2f6a
+size 122461

logs/diffusion-isp/events.out.tfevents.1696883562.gpu047.7817.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd32d2c2216b007c017c3f4cf802b4c54da1901fad5db15daa835a98ad3d5c7e
+size 98088

logs/diffusion-isp/events.out.tfevents.1696952816.gpu038.31999.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4081c9b159da3a179c62ad0e0890f0f58dcc1413f2c7e12d735c933a706bba3e
+size 24588

logs/diffusion-isp/events.out.tfevents.1696977884.gpu008.22282.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:829c047551f1097915dc1ab48d74b40c57e8f05e3a71b9c3ea709a81f4304f8e
+size 3910

logs/diffusion-isp/events.out.tfevents.1696979969.gpu008.22612.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a07345caee8ddf2ddc8b56b6eb8e8fbb3fc58eacafd832c77e5cbdfc71fcf1
+size 4596

logs/diffusion-isp/events.out.tfevents.1696982383.gpu048.32362.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a5b8a0761261bdcc498100f745eed9bd5ee42744ffa5a74d1b597e0920c7a7
+size 88

model_index.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "StableDiffusionInstructPix2PixPipeline",
+  "_diffusers_version": "0.22.0.dev0",
+  "_name_or_path": "timbrooks/instruct-pix2pix",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "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": "/h/rishit/.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": "4.34.0",
+  "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 +1,22 @@
+{
+  "_class_name": "EulerAncestralDiscreteScheduler",
+  "_diffusers_version": "0.22.0.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",
+  "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": "4.34.0",
+  "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/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|endoftext|>": 49407,
+  "<|startoftext|>": 49406
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "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",
+  "tokenizer_file": null,
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,67 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.22.0.dev0",
+  "_name_or_path": "/scratch/ssd004/scratch/rishit/diffusion-isp-model-new/checkpoint-4000",
+  "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",
+  "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 sha256:5f09a76479ed684c97538bf5d233edd477b6ecdd2c9f51681cf44593bce186c3
+size 3438213624

vae/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.22.0.dev0",
+  "_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,
+  "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