End of training

checkpoint-5000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938ea79212d90200021e75c637ca7ec967b22ce9ede70875153f19e082c2cf96
+size 34654912

checkpoint-5000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76c83c11a5c34f527de8ba7250faa25b2bc8322cdc5dc29997fda8faf5ab4ca
+size 14864

checkpoint-5000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea34278c09641c6174690299788682ca009306a6b3f5376fbad50a289b86e8e2
+size 1000

checkpoint-5000/unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "paint-by-inpaint/add-base",
+  "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-5000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55e4ec43afaad2c9d080db0c1e6936904effa13d015f8c0222c2122a742e606
+size 3438213624

checkpoint-5000/unet_ema/config.json

@@ -0,0 +1,75 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "paint-by-inpaint/add-base",
+  "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": 5000,
+  "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",
+  "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,
+  "update_after_step": 0,
+  "use_ema_warmup": false,
+  "use_linear_projection": false
+}

checkpoint-5000/unet_ema/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55e4ec43afaad2c9d080db0c1e6936904effa13d015f8c0222c2122a742e606
+size 3438213624

emb_opt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ed3168510d5fd19610053abcaa933fecb4c2bdda94ece513ba708fc0e5c017
+size 17326456

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
+  }
+}

image_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "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": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2"
+}

image_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b33d2a3a643650857672e880ccf73adbaf114fbbadec36d142ee9d48af7e20
+size 1215912728

logs/instruct-pix2pix/1732652515.441852/events.out.tfevents.1732652515.plato2.4108301.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d733666def5fd1dc7fb588f78b677796fce16fbc38dacef2d17afc9345f5e527
+size 2405

logs/instruct-pix2pix/1732652515.576361/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: ADT1999/project_from_PIPE-bug
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 2
+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: 1000
+mixed_precision: 'no'
+non_ema_revision: null
+num_train_epochs: 1
+num_validation_images: 4
+object_image_column: object_image
+original_image_column: original_image
+output_dir: instruct-pix2pix-model-20const
+pretrained_model_name_or_path: ''
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 224
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+target_image_column: target_image
+train_batch_size: 8
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+val_image_url: null
+val_image_url2: null
+validation_epochs: 1
+variant: null

logs/instruct-pix2pix/1732658328.2754567/events.out.tfevents.1732658328.plato2.4114498.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58aeda7c5de972a8eb192ac8de366be7b5297abeb03464ed8bc0a8583f9dd6d9
+size 2403

logs/instruct-pix2pix/1732658328.3103662/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: ADT1999/project_from_PIPE-bug
+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: cosine
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 40000
+mixed_precision: 'no'
+non_ema_revision: null
+num_train_epochs: 54
+num_validation_images: 4
+object_image_column: object_image
+original_image_column: original_image
+output_dir: instruct-pix2pix-model-20const
+pretrained_model_name_or_path: ''
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 224
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+target_image_column: target_image
+train_batch_size: 12
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+val_image_url: null
+val_image_url2: null
+validation_epochs: 1
+variant: null

logs/instruct-pix2pix/1732658545.1273856/events.out.tfevents.1732658545.plato2.4115018.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d26c10d59e0bdda6cf6d813331931290a6f653274007ca93ea5dabd34073bca
+size 2403

logs/instruct-pix2pix/1732658545.2209826/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: ADT1999/project_from_PIPE-bug
+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: cosine
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 10000
+mixed_precision: 'no'
+non_ema_revision: null
+num_train_epochs: 23
+num_validation_images: 4
+object_image_column: object_image
+original_image_column: original_image
+output_dir: instruct-pix2pix-model-20const
+pretrained_model_name_or_path: ''
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 224
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+target_image_column: target_image
+train_batch_size: 20
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+val_image_url: null
+val_image_url2: null
+validation_epochs: 1
+variant: null

logs/instruct-pix2pix/1732658907.1384714/events.out.tfevents.1732658907.plato2.4115515.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb60cd5b2f84aa60a40dcc829a4b5ad7b9de4a27ae547d896784c68795b694d2
+size 2403

logs/instruct-pix2pix/1732658907.2218378/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: ADT1999/project_from_PIPE-bug
+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: cosine
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 8000
+mixed_precision: 'no'
+non_ema_revision: null
+num_train_epochs: 29
+num_validation_images: 4
+object_image_column: object_image
+original_image_column: original_image
+output_dir: instruct-pix2pix-model-20const
+pretrained_model_name_or_path: ''
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 224
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+target_image_column: target_image
+train_batch_size: 32
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+val_image_url: null
+val_image_url2: null
+validation_epochs: 1
+variant: null

logs/instruct-pix2pix/events.out.tfevents.1732652515.plato2.4108301.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9adbae1c983bd71b0925a8bf2d6efede481921c24f2a48821740dc2a7ae5656f
+size 48961

logs/instruct-pix2pix/events.out.tfevents.1732658327.plato2.4114498.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c519ce43f88224ae4e630e3fbf5319d0450df7cbb761a858ea4b62760b11d66b
+size 520

logs/instruct-pix2pix/events.out.tfevents.1732658544.plato2.4115018.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c400c494ac4e89e92aa46b09f3c383a41eadba03b593985d582fe95b4e101e
+size 904

logs/instruct-pix2pix/events.out.tfevents.1732658906.plato2.4115515.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:482a3514fa9b99c368492bf7a48137b0f0e2ee2210f4789714a3acbeca4930c9
+size 391961

model_index.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "StableDiffusionInstructPix2PixImagePipeline",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "paint-by-inpaint/add-base",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerAncestralDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,16 @@
+{
+  "_class_name": "EulerAncestralDiscreteScheduler",
+  "_diffusers_version": "0.31.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "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": "/home/adi.tsach/.cache/huggingface/hub/models--paint-by-inpaint--add-base/snapshots/79753a54092b836c77292b592f5c8c2e884728ef/text_encoder",
+  "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": "float32",
+  "transformers_version": "4.44.2",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3d6454dd2d23414b56aa1b5858a72487a656937847b6fea8d0606d7a42cdbc
+size 492265168

tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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": "0.31.0.dev0",
+  "_name_or_path": "paint-by-inpaint/add-base",
+  "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:c55e4ec43afaad2c9d080db0c1e6936904effa13d015f8c0222c2122a742e606
+size 3438213624

vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "paint-by-inpaint/add-base",
+  "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,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35710aa69434a828cf1135b421ce0f88369ebe7c274fa248270e4c4af965aaf4
+size 334643268