update

feature_extractor/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
+  }
+}

feature_extractor/preprocessor_config.json

@@ -14,7 +14,7 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "CLIPFeatureExtractor",
+  "image_processor_type": "CLIPImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,

logs/text2image-fine-tune/1676440930.554518/hparams.yml

@@ -1,43 +0,0 @@
-adam_beta1: 0.9
-adam_beta2: 0.999
-adam_epsilon: 1.0e-08
-adam_weight_decay: 0.01
-allow_tf32: false
-cache_dir: null
-caption_column: text
-center_crop: true
-checkpointing_steps: 500
-dataloader_num_workers: 0
-dataset_config_name: null
-dataset_name: JAWCF/maps
-enable_xformers_memory_efficient_attention: false
-gradient_accumulation_steps: 4
-gradient_checkpointing: true
-hub_model_id: null
-hub_token: null
-image_column: image
-learning_rate: 1.0e-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: 500
-mixed_precision: null
-non_ema_revision: null
-num_train_epochs: 250
-output_dir: sd-maps-500
-pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
-push_to_hub: false
-random_flip: true
-report_to: tensorboard
-resolution: 512
-resume_from_checkpoint: null
-revision: null
-scale_lr: false
-seed: null
-train_batch_size: 1
-train_data_dir: null
-use_8bit_adam: false
-use_ema: true

logs/text2image-fine-tune/1676449032.4436474/hparams.yml

@@ -1,43 +0,0 @@
-adam_beta1: 0.9
-adam_beta2: 0.999
-adam_epsilon: 1.0e-08
-adam_weight_decay: 0.01
-allow_tf32: false
-cache_dir: null
-caption_column: text
-center_crop: true
-checkpointing_steps: 500
-dataloader_num_workers: 0
-dataset_config_name: null
-dataset_name: JAWCF/maps
-enable_xformers_memory_efficient_attention: false
-gradient_accumulation_steps: 4
-gradient_checkpointing: true
-hub_model_id: null
-hub_token: null
-image_column: image
-learning_rate: 1.0e-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: 500
-mixed_precision: null
-non_ema_revision: null
-num_train_epochs: 250
-output_dir: sd-maps-500
-pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
-push_to_hub: false
-random_flip: true
-report_to: tensorboard
-resolution: 2048
-resume_from_checkpoint: null
-revision: null
-scale_lr: false
-seed: null
-train_batch_size: 1
-train_data_dir: null
-use_8bit_adam: false
-use_ema: true

logs/text2image-fine-tune/1676449386.0662346/hparams.yml

@@ -1,43 +0,0 @@
-adam_beta1: 0.9
-adam_beta2: 0.999
-adam_epsilon: 1.0e-08
-adam_weight_decay: 0.01
-allow_tf32: false
-cache_dir: null
-caption_column: text
-center_crop: true
-checkpointing_steps: 500
-dataloader_num_workers: 0
-dataset_config_name: null
-dataset_name: JAWCF/maps
-enable_xformers_memory_efficient_attention: false
-gradient_accumulation_steps: 4
-gradient_checkpointing: true
-hub_model_id: null
-hub_token: null
-image_column: image
-learning_rate: 1.0e-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: 500
-mixed_precision: null
-non_ema_revision: null
-num_train_epochs: 250
-output_dir: sd-maps-500
-pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
-push_to_hub: false
-random_flip: true
-report_to: tensorboard
-resolution: 2048
-resume_from_checkpoint: null
-revision: null
-scale_lr: false
-seed: null
-train_batch_size: 1
-train_data_dir: null
-use_8bit_adam: false
-use_ema: true

logs/text2image-fine-tune/1678859558.2680285/hparams.yml

@@ -1,43 +0,0 @@
-adam_beta1: 0.9
-adam_beta2: 0.999
-adam_epsilon: 1.0e-08
-adam_weight_decay: 0.01
-allow_tf32: false
-cache_dir: null
-caption_column: text
-center_crop: true
-checkpointing_steps: 500
-dataloader_num_workers: 0
-dataset_config_name: null
-dataset_name: JAWCF/maps
-enable_xformers_memory_efficient_attention: false
-gradient_accumulation_steps: 4
-gradient_checkpointing: true
-hub_model_id: null
-hub_token: null
-image_column: image
-learning_rate: 1.0e-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: 500
-mixed_precision: null
-non_ema_revision: null
-num_train_epochs: 125
-output_dir: sd-maps-500
-pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
-push_to_hub: false
-random_flip: true
-report_to: tensorboard
-resolution: 512
-resume_from_checkpoint: null
-revision: null
-scale_lr: false
-seed: null
-train_batch_size: 1
-train_data_dir: null
-use_8bit_adam: false
-use_ema: true

logs/text2image-fine-tune/1678933761.2569368/events.out.tfevents.1678933761.cdr2554.int.cedar.computecanada.ca.155172.1

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8079cea0f53e84d4c624a931fdd42fde7d8528508b60858e6d5f7ae766689351
-size 1908

logs/text2image-fine-tune/1678933761.2708018/hparams.yml

@@ -1,43 +0,0 @@
-adam_beta1: 0.9
-adam_beta2: 0.999
-adam_epsilon: 1.0e-08
-adam_weight_decay: 0.01
-allow_tf32: false
-cache_dir: null
-caption_column: text
-center_crop: true
-checkpointing_steps: 500
-dataloader_num_workers: 0
-dataset_config_name: null
-dataset_name: JAWCF/maps
-enable_xformers_memory_efficient_attention: false
-gradient_accumulation_steps: 4
-gradient_checkpointing: true
-hub_model_id: null
-hub_token: null
-image_column: image
-learning_rate: 1.0e-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: 500
-mixed_precision: null
-non_ema_revision: null
-num_train_epochs: 125
-output_dir: sd-maps-500
-pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
-push_to_hub: false
-random_flip: true
-report_to: tensorboard
-resolution: 512
-resume_from_checkpoint: null
-revision: null
-scale_lr: false
-seed: null
-train_batch_size: 1
-train_data_dir: null
-use_8bit_adam: false
-use_ema: true

logs/text2image-fine-tune/events.out.tfevents.1676440930.cdr2596.int.cedar.computecanada.ca.103093.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4cd704cfd318155b5cbf3ba46879eee1ae23326b38dd38e908dbe3b05186abb4
-size 24413

logs/text2image-fine-tune/events.out.tfevents.1676449032.cdr2599.int.cedar.computecanada.ca.125597.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e7e8380429a0fb709eb55df7b06856d64a6257b4fd28848b62a3bf2aafb995cc
-size 40

logs/text2image-fine-tune/events.out.tfevents.1676449386.cdr2596.int.cedar.computecanada.ca.128191.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c02060e098cd94a890ca26ba812b661f089d0d6ff7a0971224fe127a1f70c354
-size 40

logs/text2image-fine-tune/events.out.tfevents.1678859558.cdr2602.int.cedar.computecanada.ca.72747.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:43ea5cd06bb66e3d5db0fdfbd601254a3b964cdfe783a01804c0cb25991fd1fa
-size 24413

logs/text2image-fine-tune/events.out.tfevents.1678933761.cdr2554.int.cedar.computecanada.ca.155172.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:659f131d1edfe28aba16e7364bda939ebc78fcb2785e03faee559ce2fe1908ef
-size 24413

model_index.json

@@ -1,11 +1,15 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.13.0.dev0",
+  "_diffusers_version": "0.18.0.dev0",
   "feature_extractor": [
     "transformers",
-    "CLIPFeatureExtractor"
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
   ],
-  "requires_safety_checker": false,
   "scheduler": [
     "diffusers",
     "PNDMScheduler"

safety_checker/config.json

@@ -1,6 +1,6 @@
 {
-  "_commit_hash": "249dd2d739844dea6a0bc7fc27b3c1d014720b28",
-  "_name_or_path": "/home/c287wu/.cache/huggingface/diffusers/models--CompVis--stable-diffusion-v1-4/snapshots/249dd2d739844dea6a0bc7fc27b3c1d014720b28/safety_checker",
+  "_commit_hash": "59ec6bdf37d6279d3c0faf36e89ff1aa34f7ebf4",
+  "_name_or_path": "/home/admin_/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/59ec6bdf37d6279d3c0faf36e89ff1aa34f7ebf4/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],
@@ -80,17 +80,11 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.26.0",
+    "transformers_version": "4.30.2",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vocab_size": 49408
   },
-  "text_config_dict": {
-    "hidden_size": 768,
-    "intermediate_size": 3072,
-    "num_attention_heads": 12,
-    "num_hidden_layers": 12
-  },
   "torch_dtype": "float32",
   "transformers_version": null,
   "vision_config": {
@@ -167,15 +161,8 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.26.0",
+    "transformers_version": "4.30.2",
     "typical_p": 1.0,
     "use_bfloat16": false
-  },
-  "vision_config_dict": {
-    "hidden_size": 1024,
-    "intermediate_size": 4096,
-    "num_attention_heads": 16,
-    "num_hidden_layers": 24,
-    "patch_size": 14
   }
 }

safety_checker/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:193490b58ef62739077262e833bf091c66c29488058681ac25cf7df3d8190974
-size 1216061799
+oid sha256:66722b66269c4c55c4bec40ddd25b3e45d84e1305079f5f8414cd54348ac7dc3
+size 948842496

safety_checker/safety_checker/config.json

@@ -0,0 +1,168 @@
+{
+  "_commit_hash": "59ec6bdf37d6279d3c0faf36e89ff1aa34f7ebf4",
+  "_name_or_path": "/home/admin_/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/59ec6bdf37d6279d3c0faf36e89ff1aa34f7ebf4/safety_checker",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.30.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.30.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

logs/text2image-fine-tune/1678859558.2620409/events.out.tfevents.1678859558.cdr2602.int.cedar.computecanada.ca.72747.1 → safety_checker/safety_checker/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c3c75fa77999f1381a2fb8471f00f34d20d6c26e842dbf292a6ce6abda6f4e
-size 1908
+oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
+size 1216064769

safety_checker/vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.18.0.dev0",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "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"
+  ]
+}

logs/text2image-fine-tune/1676440930.547604/events.out.tfevents.1676440930.cdr2596.int.cedar.computecanada.ca.103093.1 → safety_checker/vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5954b826e12e62d06bf0e2675ef455a61a061222bbad6af02683690f128ab0c
-size 1908
+oid sha256:aa8c1b74b3e2781e4347b9b350203597674d8860a4338b46431de760c3a5dd22
+size 167407857

scheduler/scheduler/scheduler_config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.18.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null
+}

text_encoder/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "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": 512,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "vocab_size": 49408
+}

logs/text2image-fine-tune/1676449386.059543/events.out.tfevents.1676449386.cdr2596.int.cedar.computecanada.ca.128191.1 → text_encoder/text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2709733af4b8abb109add9039242bd14e0ff181d032d299b3165caf4aae60ab2
-size 1908
+oid sha256:6a34f30098988d85dc0fb0fc272a842ebcf552e2ebc6ce4adbcf3695d08e8a90
+size 246188833

tokenizer/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/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/unet/config.json

@@ -0,0 +1,62 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.18.0.dev0",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "attention_head_dim": 8,
+  "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,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "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_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,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3ae8819c2867ff1843b4ad3fc4e953ab82c551cc7bff5584087a0c7822f541
+size 3438375973

vae/vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.18.0.dev0",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "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"
+  ]
+}

logs/text2image-fine-tune/1676449032.426536/events.out.tfevents.1676449032.cdr2599.int.cedar.computecanada.ca.125597.1 → vae/vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:959ab434d6b05d0505fffb956c9179a931cc971c9812ac3151b4e2903451d1a7
-size 1908
+oid sha256:aa8c1b74b3e2781e4347b9b350203597674d8860a4338b46431de760c3a5dd22
+size 167407857