add my first model config file :)

sdsofubi/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
+  }
+}

sdsofubi/logs/text2image-fine-tune/1684345931.2007685/events.out.tfevents.1684345931.k-Z690-Taichi.7384.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18b8bf1bc21a62bdc2435f92b633d45c53aef9b6a451778d60e8e780e8360ba
+size 2180

sdsofubi/logs/text2image-fine-tune/1684345931.201548/hparams.yml

@@ -0,0 +1,49 @@
+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
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: sofubi2
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_pertubation: 0
+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: 15000
+mixed_precision: null
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 91
+output_dir: sdsofubi
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+push_to_hub: false
+random_flip: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+validation_epochs: 5

sdsofubi/logs/text2image-fine-tune/1684345962.192576/events.out.tfevents.1684345962.k-Z690-Taichi.7522.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17c509449e3e3fc184650e1a202b72181f5b6bac2d0c5045211e505e1890d4e
+size 2180

sdsofubi/logs/text2image-fine-tune/1684345962.1934202/hparams.yml

@@ -0,0 +1,49 @@
+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
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: sofubi2
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_pertubation: 0
+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: 15000
+mixed_precision: null
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 46
+output_dir: sdsofubi
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+push_to_hub: false
+random_flip: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+validation_epochs: 5

sdsofubi/logs/text2image-fine-tune/1684346008.049436/events.out.tfevents.1684346008.k-Z690-Taichi.7655.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39412af2513912c5a326a7266ec88f63eafa2fbb25a1a482b6ef6b4848460ce
+size 2180

sdsofubi/logs/text2image-fine-tune/1684346008.0501857/hparams.yml

@@ -0,0 +1,49 @@
+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: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: sofubi2
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_pertubation: 0
+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: 15000
+mixed_precision: null
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 23
+output_dir: sdsofubi
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+validation_epochs: 5

sdsofubi/logs/text2image-fine-tune/1684346033.5972078/events.out.tfevents.1684346033.k-Z690-Taichi.7786.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dcdbf3bbf882432fcd1e9e8e15f67abb16f9dc452f8a925088156636de58099
+size 2180

sdsofubi/logs/text2image-fine-tune/1684346033.5979536/hparams.yml

@@ -0,0 +1,49 @@
+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: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: sofubi2
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_pertubation: 0
+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: 15000
+mixed_precision: null
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 23
+output_dir: sdsofubi
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+validation_epochs: 5

sdsofubi/logs/text2image-fine-tune/1684409354.8168964/events.out.tfevents.1684409354.k-Z690-Taichi.3962.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47bc901aee5984aadcf8de7e61cb3b1262d2d2020a4ae43a4a9485435ace9870
+size 2244

sdsofubi/logs/text2image-fine-tune/1684409354.8176308/hparams.yml

@@ -0,0 +1,49 @@
+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: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: sofubi2
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_pertubation: 0
+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: 15000
+mixed_precision: null
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 23
+output_dir: sdsofubi
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+validation_epochs: 5

sdsofubi/logs/text2image-fine-tune/1684409415.3129587/events.out.tfevents.1684409415.k-Z690-Taichi.4195.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e23c58daa3a36b8251ddeff1889bf656154faad0285c4f37c451224c17ab97f1
+size 2244

sdsofubi/logs/text2image-fine-tune/1684409415.3136842/hparams.yml

@@ -0,0 +1,49 @@
+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: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: sofubi2
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_pertubation: 0
+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: 15000
+mixed_precision: null
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 23
+output_dir: sdsofubi
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+validation_epochs: 5

sdsofubi/logs/text2image-fine-tune/1684413084.87153/events.out.tfevents.1684413084.k-Z690-Taichi.6514.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4812f03b8a34f10fbac55937e3b21454ad72d4ba8fb3d86812a40c6234137c93
+size 2244

sdsofubi/logs/text2image-fine-tune/1684413084.8723006/hparams.yml

@@ -0,0 +1,49 @@
+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: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: sofubi2
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_pertubation: 0
+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: 15000
+mixed_precision: null
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 23
+output_dir: sdsofubi
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+validation_epochs: 5

sdsofubi/logs/text2image-fine-tune/1684413168.506949/events.out.tfevents.1684413168.k-Z690-Taichi.6677.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a10720a09dd6ba4034833be033d0d3747fb2ad77a456b449fa4945c2ba7f9a
+size 2244

sdsofubi/logs/text2image-fine-tune/1684413168.5076537/hparams.yml

@@ -0,0 +1,49 @@
+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: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: sofubi2
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_pertubation: 0
+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: 15000
+mixed_precision: null
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 23
+output_dir: sdsofubi
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+validation_epochs: 5

sdsofubi/logs/text2image-fine-tune/1684413285.905263/events.out.tfevents.1684413285.k-Z690-Taichi.6897.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ddf8e0ac8b54a04196ad6d7878c166e584cdf83cb1f8890cbb7611c95aca370
+size 2244

sdsofubi/logs/text2image-fine-tune/1684413285.906191/hparams.yml

@@ -0,0 +1,49 @@
+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: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: sofubi2
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_pertubation: 0
+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: 15000
+mixed_precision: null
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 23
+output_dir: sdsofubi
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+validation_epochs: 5

sdsofubi/logs/text2image-fine-tune/1684413558.5765154/events.out.tfevents.1684413558.k-Z690-Taichi.7069.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd0c883caaf3db76b586564a1949b50aae8484905519c73133e382c9e33cf22
+size 2244

sdsofubi/logs/text2image-fine-tune/1684413558.5772042/hparams.yml

@@ -0,0 +1,49 @@
+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: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: sofubi2
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_pertubation: 0
+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: 15000
+mixed_precision: null
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 23
+output_dir: sdsofubi
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+validation_epochs: 5

sdsofubi/logs/text2image-fine-tune/1684414815.3861752/events.out.tfevents.1684414815.k-Z690-Taichi.7673.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c2a94036169f2f7cfa89ec817c62362ebc0240d9e8fe1c18da13cbc7dcdd0b
+size 2244

sdsofubi/logs/text2image-fine-tune/1684414815.3869019/hparams.yml

@@ -0,0 +1,49 @@
+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: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: sofubi2
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+input_pertubation: 0
+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: 15000
+mixed_precision: null
+noise_offset: 0
+non_ema_revision: null
+num_train_epochs: 23
+output_dir: sdsofubi
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+validation_epochs: 5

sdsofubi/logs/text2image-fine-tune/events.out.tfevents.1684345931.k-Z690-Taichi.7384.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff346e676754aebfbfb17fed4e2ecedb6a99e9757099d9552047e82a7b5ef70
+size 88

sdsofubi/logs/text2image-fine-tune/events.out.tfevents.1684345962.k-Z690-Taichi.7522.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53a6b4be680ee5927f3d77c89f2c09a5bffc66074fbcc9e85aabf0150d3ba66
+size 88

sdsofubi/logs/text2image-fine-tune/events.out.tfevents.1684346008.k-Z690-Taichi.7655.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561fefd5be0ff7b4f7b1073284888a4cb91accef97a173906d305a324f148247
+size 88

sdsofubi/logs/text2image-fine-tune/events.out.tfevents.1684346033.k-Z690-Taichi.7786.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d7e99c52d464153f56889cf5ea7c1f535d9ab1fc0c7c1ff130cc28b7cc84986
+size 391961

sdsofubi/logs/text2image-fine-tune/events.out.tfevents.1684409354.k-Z690-Taichi.3962.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92417cde890c7420fc7eda973b4d8f5133d395735db9337859ae8bf698283915
+size 88

sdsofubi/logs/text2image-fine-tune/events.out.tfevents.1684409415.k-Z690-Taichi.4195.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c6ee56882df873f1fbb13a33930618a8e32cc1a7a1e650e438d42ec6ed4f436
+size 367588

sdsofubi/logs/text2image-fine-tune/events.out.tfevents.1684413084.k-Z690-Taichi.6514.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660795f64993de5e06f089de4f8f310b7a2378a09a5e1b4e86f85dd8e7990357
+size 137

sdsofubi/logs/text2image-fine-tune/events.out.tfevents.1684413168.k-Z690-Taichi.6677.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d70c44bc27f3f49169b35a294392d6c37a1386268e965509a90861eb61e858
+size 137

sdsofubi/logs/text2image-fine-tune/events.out.tfevents.1684413285.k-Z690-Taichi.6897.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb3c44e708be95427959d47087b524bd7c06d8a794ac91eb8ce244efd934ebb
+size 137

sdsofubi/logs/text2image-fine-tune/events.out.tfevents.1684413558.k-Z690-Taichi.7069.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35754fa3238106b808734a01cef59ddc7cde80118efe53e13e29e5b3d1ae23b
+size 137

sdsofubi/logs/text2image-fine-tune/events.out.tfevents.1684414815.k-Z690-Taichi.7673.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d51273493d9673cc68d5d79e67213cf1c1f66409351d4926bc82f7ca0f14fd
+size 137

sdsofubi/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.17.0.dev0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

sdsofubi/safety_checker/config.json

@@ -0,0 +1,168 @@
+{
+  "_commit_hash": "aa9ba505e1973ae5cd05f5aedd345178f52f8e6a",
+  "_name_or_path": "/home/k/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/aa9ba505e1973ae5cd05f5aedd345178f52f8e6a/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": "4.29.2",
+    "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": "4.29.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

sdsofubi/safety_checker/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
+size 1216064769

sdsofubi/scheduler/scheduler_config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.17.0.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
+}

sdsofubi/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "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": "4.29.2",
+  "vocab_size": 49408
+}

sdsofubi/text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a34f30098988d85dc0fb0fc272a842ebcf552e2ebc6ce4adbcf3695d08e8a90
+size 246188833

sdsofubi/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
+  }
+}

sdsofubi/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
+  }
+}

sdsofubi/unet/config.json

@@ -0,0 +1,61 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.17.0.dev0",
+  "_name_or_path": "sdsofubi/checkpoint-15000",
+  "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,
+  "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
+}

sdsofubi/unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e75910994ad6e437c1b2989f4793fd5bc94b4dc47e32d9c614a8200f3544d12
+size 3438375973

sdsofubi/vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.17.0.dev0",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "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"
+  ]
+}

sdsofubi/vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa8c1b74b3e2781e4347b9b350203597674d8860a4338b46431de760c3a5dd22
+size 167407857