End of training

README.md

@@ -0,0 +1,17 @@
+
+---
+license: creativeml-openrail-m
+base_model: stabilityai/stable-diffusion-2-1
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- textual_inversion
+inference: true
+---
+    
+# Textual inversion text2image fine-tuning - briannlongzhao/0
+These are textual inversion adaption weights for stabilityai/stable-diffusion-2-1. You can find some example images in the following. 
+
+

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
+  }
+}

learned_embeds.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e35299370efccb3f7280ace07784d1de9822112778591c0e34d5beae9c406a
+size 4216

logs/textual_inversion/1706280421.578669/events.out.tfevents.1706280421.iLab1.2204967.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745a85edf2f6ea4b0a997f5bd7f62a3e3780147db4226ffae02bb7639482d08c
+size 2514

logs/textual_inversion/1706280421.5903156/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
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_name: American robin
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+idx: 0
+initializer_token: American robin
+learnable_property: object
+learning_rate: 0.004
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 3000
+mixed_precision: bf16
+no_safe_serialization: false
+num_train_epochs: 22
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_models/0
+placeholder_token: <American robin>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
+push_to_hub: false
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+wnid: n01558993

logs/textual_inversion/1706280825.454071/events.out.tfevents.1706280825.iLab1.2206154.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9b8a1a6c07ff7c7667d98d2aece1ad433fd664d3b1d1003c6993a002086860
+size 2514

logs/textual_inversion/1706280825.4620266/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
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_name: American robin
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+idx: 0
+initializer_token: American robin
+learnable_property: object
+learning_rate: 0.004
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 3000
+mixed_precision: bf16
+no_safe_serialization: false
+num_train_epochs: 24
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_models/0
+placeholder_token: <American robin>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
+push_to_hub: false
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+wnid: n01558993

logs/textual_inversion/1706350703.133833/events.out.tfevents.1706350703.iLab1.2382622.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b491e4c0ce0c5f988d6c46acdde6ce9708390ee339e7647b364870f37d13e9
+size 2514

logs/textual_inversion/1706350703.1423192/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
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_name: American robin
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+idx: 0
+initializer_token: American robin
+learnable_property: object
+learning_rate: 0.004
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 3000
+mixed_precision: bf16
+no_safe_serialization: false
+num_train_epochs: 24
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_models/0
+placeholder_token: <American robin>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
+push_to_hub: false
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+wnid: n01558993

logs/textual_inversion/1706371045.0783992/events.out.tfevents.1706371045.iLab1.2434479.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a5e68db49653f6d4b3ac3fcd1a81cebafb203d1452df8e9647df682027f6e6
+size 2514

logs/textual_inversion/1706371045.0874188/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
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_name: American robin
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+idx: 0
+initializer_token: American robin
+learnable_property: object
+learning_rate: 0.004
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 5000
+mixed_precision: fp16
+no_safe_serialization: false
+num_train_epochs: 40
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_models/0
+placeholder_token: <American robin>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
+push_to_hub: false
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+wnid: n01558993

logs/textual_inversion/1706371141.669214/events.out.tfevents.1706371141.iLab1.2434814.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9b4aa6f1f581febb38aeb81afb25ad88adeda4b647f84ba522201356ab693f
+size 2514

logs/textual_inversion/1706371141.6791615/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
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_name: American robin
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+idx: 0
+initializer_token: American robin
+learnable_property: object
+learning_rate: 0.004
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 5000
+mixed_precision: fp16
+no_safe_serialization: false
+num_train_epochs: 40
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_models/0
+placeholder_token: <American robin>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
+push_to_hub: false
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+wnid: n01558993

logs/textual_inversion/1706371354.8574433/events.out.tfevents.1706371354.iLab1.2435567.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd557b45b3f9b4f2f23257828a47c474b9d958a052d1872d70925962908146eb
+size 2514

logs/textual_inversion/1706371354.8662636/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
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_name: American robin
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+idx: 0
+initializer_token: American robin
+learnable_property: object
+learning_rate: 0.004
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 5000
+mixed_precision: fp16
+no_safe_serialization: false
+num_train_epochs: 40
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_models/0
+placeholder_token: <American robin>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
+push_to_hub: false
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+wnid: n01558993

logs/textual_inversion/1706371561.3719206/events.out.tfevents.1706371561.iLab1.2436226.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee803061af5876651aeaa6844c08840b9b5fc9695b287e31831e6aa9468db8b7
+size 2514

logs/textual_inversion/1706371561.3834906/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
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_name: American robin
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+idx: 0
+initializer_token: American robin
+learnable_property: object
+learning_rate: 0.004
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 5000
+mixed_precision: fp16
+no_safe_serialization: false
+num_train_epochs: 40
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_models/0
+placeholder_token: <American robin>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
+push_to_hub: false
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+wnid: n01558993

logs/textual_inversion/1706371717.5312033/events.out.tfevents.1706371717.iLab1.2436700.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95310f2d9d843b2b9bd135575c2760104ba218dae12db0ef1ca0fd7bbc69e9eb
+size 2514

logs/textual_inversion/1706371717.5418997/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
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_name: American robin
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+idx: 0
+initializer_token: American robin
+learnable_property: object
+learning_rate: 0.004
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 5000
+mixed_precision: fp16
+no_safe_serialization: false
+num_train_epochs: 2500
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_models/0
+placeholder_token: <American robin>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
+push_to_hub: false
+repeats: 1
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+wnid: n01558993

logs/textual_inversion/1706371855.6283345/events.out.tfevents.1706371855.iLab1.2437159.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3401fdf9f66cdeeac74d2c57643f9ef65fc4bac3eed23f2ba0f9a30d17a39bbe
+size 2514

logs/textual_inversion/1706371855.636531/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
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_name: American robin
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+idx: 0
+initializer_token: American robin
+learnable_property: object
+learning_rate: 0.004
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 10
+mixed_precision: fp16
+no_safe_serialization: false
+num_train_epochs: 5
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_models/0
+placeholder_token: <American robin>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
+push_to_hub: false
+repeats: 1
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+wnid: n01558993

logs/textual_inversion/1706371949.914301/events.out.tfevents.1706371949.iLab1.2437530.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f76099bcddaf3422f9f89cda26a4e67b6a6bb2378bfee193272d9a26958589
+size 2514

logs/textual_inversion/1706371949.922713/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
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_name: American robin
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+idx: 0
+initializer_token: American robin
+learnable_property: object
+learning_rate: 0.004
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 10
+mixed_precision: fp16
+no_safe_serialization: false
+num_train_epochs: 5
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_models/0
+placeholder_token: <American robin>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
+push_to_hub: false
+repeats: 1
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+wnid: n01558993

logs/textual_inversion/1706372280.9472425/events.out.tfevents.1706372280.iLab1.2438547.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f95fb5aecd71685651e6b422a26b3bc453b5e7ff6072659cfb23f3d246aa661
+size 2514

logs/textual_inversion/1706372280.955396/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
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_name: American robin
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+idx: 0
+initializer_token: American robin
+learnable_property: object
+learning_rate: 0.004
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 10
+mixed_precision: fp16
+no_safe_serialization: false
+num_train_epochs: 5
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_models/0
+placeholder_token: <American robin>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
+push_to_hub: true
+repeats: 1
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+wnid: n01558993

logs/textual_inversion/events.out.tfevents.1706280421.iLab1.2204967.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b67d4ba724e76074496fd1b42f54fd96d9545a3983168974be48e8e726eb127
+size 88

logs/textual_inversion/events.out.tfevents.1706280825.iLab1.2206154.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc62365dfb792c3b56d22fbae0c8af10b5063547d1c053cce375683285ff5007
+size 12048

logs/textual_inversion/events.out.tfevents.1706350703.iLab1.2382622.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa6c033836a370aa050a8b4cf3a933c9edc818588b1b08339e060eda28f432b
+size 11556

logs/textual_inversion/events.out.tfevents.1706371045.iLab1.2434479.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c28ee53edaa43ad8d6abbe9eeaae5959a881b518f3fa931c373947f87c8d3544
+size 10162

logs/textual_inversion/events.out.tfevents.1706371141.iLab1.2434814.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93396b9922cf0d9321a69ff582a983b08722a5f985b9a0b4751787572d5a5efd
+size 2536

logs/textual_inversion/events.out.tfevents.1706371354.iLab1.2435567.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b06ec4d04aae49850325fb794c02c2816029c27fc953f228538ec6cf6a1b6bee
+size 88

logs/textual_inversion/events.out.tfevents.1706371561.iLab1.2436226.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c452f77e9ae84f6ed39dfe9b17a797ec210de72290041ea337a6e69bfac6554
+size 4586

logs/textual_inversion/events.out.tfevents.1706371717.iLab1.2436700.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb03591e96023d386928d08a7c05167e947afbf2f46a565d7d46c18c27b5fbf
+size 2946

logs/textual_inversion/events.out.tfevents.1706371855.iLab1.2437159.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2b56f3109458ca4b86baa3b99525952d2d4b964c4b0f723a8f0c5b60e425e5
+size 2126

logs/textual_inversion/events.out.tfevents.1706371949.iLab1.2437530.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28eea5dff7c2e72ef1d69fd08232e7f7968f6d4082f6b303c9a39a0e30800dcc
+size 2126

logs/textual_inversion/events.out.tfevents.1706372280.iLab1.2438547.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f78378d79247efcff1edcf27a07b3deb691642f2b12edd3ccf9318e21a87dc6
+size 2126

model_index.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.25.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "vocab_size": 49409
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc0fe2724055322732c6e6f99bd8723df319d483c88a7e3c83d776e6aeadf4d
+size 1361601112

tokenizer/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<American robin>": 49408
+}

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": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "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": 1024,
+  "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": 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_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": 96,
+  "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": true,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a3a4d7978884c5e4ef00b62641b1b544b257be2f6715d984188610ad6475ad2
+size 1731904736

vae/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.25.1",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
+  "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": 768,
+  "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 sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
+size 167335342