End of training

README.md

@@ -0,0 +1,17 @@
+
+---
+license: creativeml-openrail-m
+base_model: stabilityai/stable-diffusion-2
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- textual_inversion
+inference: true
+---
+    
+# Textual inversion text2image fine-tuning - Kabuto009/textual_inversion_cat
+These are textual inversion adaption weights for stabilityai/stable-diffusion-2. You can find some example images in the following. 
+
+

feature_extractor/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "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
+  },
+  "use_square_size": false
+}

learned_embeds.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b215bc2d85c3e6f607896b1f69c0ec1047f478154e8e2821f7ebbc6fc406cdb
+size 4208

logs/textual_inversion/1700104500.2501602/events.out.tfevents.1700104500.3f82a5ecc45f.3814.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc3a2728f23106347012542ce2d09733911fc6cc7f7377059ba53ae3f400dcfd
+size 2323

logs/textual_inversion/1700104500.2529488/hparams.yml

@@ -0,0 +1,47 @@
+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
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: toy
+learnable_property: object
+learning_rate: 0.01
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 3000
+mixed_precision: 'no'
+no_safe_serialization: false
+num_train_epochs: 100
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_cat
+placeholder_token: <cat-toy>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 768
+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: ./cat
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100

logs/textual_inversion/1700129666.9990883/events.out.tfevents.1700129666.3f82a5ecc45f.10272.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f48cc2c415a912c67ef178a8d215b3c7f1f11ec46617b28eaac346ad5df4ea
+size 2323

logs/textual_inversion/1700129667.0014312/hparams.yml

@@ -0,0 +1,47 @@
+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
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: toy
+learnable_property: object
+learning_rate: 0.002
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 3000
+mixed_precision: 'no'
+no_safe_serialization: false
+num_train_epochs: 20
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_cat
+placeholder_token: <cat-toy>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 768
+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: ./cat
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100

logs/textual_inversion/1700191691.8335083/events.out.tfevents.1700191691.3f82a5ecc45f.12854.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ba503fe225a208d37d9712fba19f7b8fb97c46155a4bbd957b297cdbf7bc17a
+size 2323

logs/textual_inversion/1700191691.835869/hparams.yml

@@ -0,0 +1,47 @@
+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
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: toy
+learnable_property: object
+learning_rate: 0.002
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 3000
+mixed_precision: 'no'
+no_safe_serialization: false
+num_train_epochs: 20
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_cat
+placeholder_token: <cat-toy>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 768
+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: ./cat
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100

logs/textual_inversion/1700192066.441311/events.out.tfevents.1700192066.3f82a5ecc45f.13950.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0362e3bb72c2b6f43856aa05504955595ca3bba2e89c359b4299375e00b33059
+size 2323

logs/textual_inversion/1700192066.4436088/hparams.yml

@@ -0,0 +1,47 @@
+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
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: toy
+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: 'no'
+no_safe_serialization: false
+num_train_epochs: 40
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_cat
+placeholder_token: <cat-toy>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 768
+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: ./cat
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100

logs/textual_inversion/1700193074.7362921/events.out.tfevents.1700193074.3f82a5ecc45f.14404.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be28540f46c6ee7173344e664025069a325ad44458fe106873724cdc4071b800
+size 2323

logs/textual_inversion/1700193074.7385833/hparams.yml

@@ -0,0 +1,47 @@
+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
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: toy
+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: 'no'
+no_safe_serialization: false
+num_train_epochs: 40
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_cat
+placeholder_token: <cat-toy>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 768
+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: ./cat
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100

logs/textual_inversion/1700211288.115931/events.out.tfevents.1700211288.3f82a5ecc45f.16238.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791d7b98c5526783acafb46e1fc48318dc0de2cf9e0662eaac5bdeadc4383978
+size 2323

logs/textual_inversion/1700211288.1182225/hparams.yml

@@ -0,0 +1,47 @@
+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
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: toy
+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: 1
+mixed_precision: 'no'
+no_safe_serialization: false
+num_train_epochs: 1
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_cat
+placeholder_token: <cat-toy>
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 768
+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: ./cat
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100

logs/textual_inversion/events.out.tfevents.1700104499.3f82a5ecc45f.3814.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce251c88069d81effc028b61debb4ed96a24219e14b2e156dbddba80bad42097
+size 18690

logs/textual_inversion/events.out.tfevents.1700129666.3f82a5ecc45f.10272.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428a37932a06ce82c40d74750277499aa5f280b7000ccfde1ebe06e124328fc2
+size 1470

logs/textual_inversion/events.out.tfevents.1700191691.3f82a5ecc45f.12854.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30019da3786bf0eaab32fb4cc585161bca74516c7c69df3a41a18b0ccc6b9be6
+size 486

logs/textual_inversion/events.out.tfevents.1700192066.3f82a5ecc45f.13950.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f0b07e63fb8719733965f4bb5cb2967119d994079147978b04582755cdda30
+size 744

logs/textual_inversion/events.out.tfevents.1700193074.3f82a5ecc45f.14404.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07b10551597c090ceda59c5379903baea07697568eb529ff5aee275a405ff5d
+size 170

logs/textual_inversion/events.out.tfevents.1700211288.3f82a5ecc45f.16238.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a13ee934565e31bb7390c50e55721fabb11e471afcfd265d4ffa71037ad67b2
+size 170

model_index.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.24.0.dev0",
+  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "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": "0.24.0.dev0",
+  "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",
+  "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": "4.35.2",
+  "vocab_size": 49409
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e3ffc181082af5f8b9b9a976b2b39e9c0ae846734d4e729097a16581d03b18
+size 1361600400

tokenizer/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<cat-toy>": 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 +1,46 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    },
+    "49408": {
+      "content": "<cat-toy>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.24.0.dev0",
+  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "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": false,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00428c452831dbbb1d3aef29105913252baef9de50543ed28c7cb958256e189
+size 3463726504

vae/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.24.0.dev0",
+  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "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 sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
+size 334643268