Add files using upload-large-folder tool

checkpoint_1000/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_1000",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_1000/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_10000/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_10000",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_10000/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_11000/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_11000",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_11000/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_12000/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_12000",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_12000/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_2000/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_2000",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_2000/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_3000/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_3000",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_3000/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_4000/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_4000",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_4000/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_5000/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_5000",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_5000/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_6000/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_6000",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_6000/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_7000/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_7000",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_7000/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_8000/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_8000",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_8000/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_8000/scheduler/scheduler_config.json

@@ -0,0 +1,17 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.15.0.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": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "steps_offset": 1,
+  "thresholding": false,
+  "trained_betas": null
+}

checkpoint_8000/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "./model-hf",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "vocab_size": 49408
+}

checkpoint_8000/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
+  }
+}

checkpoint_8000/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
+  }
+}

checkpoint_8000/unet/config.json

@@ -0,0 +1,52 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.15.0.dev0",
+  "_name_or_path": "./model-hf",
+  "act_fn": "silu",
+  "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,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "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_time_scale_shift": "default",
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

checkpoint_8000/vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.15.0.dev0",
+  "_name_or_path": "./model-hf",
+  "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"
+  ]
+}

checkpoint_9000/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_9000",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_9000/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_9000/scheduler/scheduler_config.json

@@ -0,0 +1,17 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.15.0.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": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "steps_offset": 1,
+  "thresholding": false,
+  "trained_betas": null
+}

checkpoint_9000/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "./model-hf",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "vocab_size": 49408
+}

checkpoint_9000/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
+  }
+}

checkpoint_9000/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
+  }
+}

checkpoint_9000/unet/config.json

@@ -0,0 +1,52 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.15.0.dev0",
+  "_name_or_path": "./model-hf",
+  "act_fn": "silu",
+  "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,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "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_time_scale_shift": "default",
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

checkpoint_9000/vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.15.0.dev0",
+  "_name_or_path": "./model-hf",
+  "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"
+  ]
+}

checkpoint_last/args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./model-hf",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "",
+  "class_prompt": "masterpiece, best quality, 1girl",
+  "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "save_sample_prompt": "masterpiece, best quality, 1girl, looking at viewer",
+  "save_sample_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": false,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 20,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 1024,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 210,
+  "max_train_steps": 13000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 5e-06,
+  "scale_lr": false,
+  "scale_lr_sqrt": false,
+  "lr_scheduler": "cosine_with_restarts",
+  "lr_warmup_steps": 100,
+  "use_8bit_adam": true,
+  "use_deepspeed_adam": false,
+  "optimizer": "adamw",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "sgd_momentum": 0.9,
+  "sgd_dampening": 0,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.01,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": true,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "",
+      "class_prompt": "masterpiece, best quality, 1girl",
+      "class_negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+      "instance_data_dir": "./instance-images",
+      "class_data_dir": "./class-images"
+    }
+  ],
+  "wandb": false,
+  "wandb_artifact": false,
+  "rm_after_wandb_saved": false,
+  "wandb_name": "Stable-Diffusion-Dreambooth",
+  "read_prompt_filename": false,
+  "read_prompt_txt": false,
+  "append_prompt": "instance",
+  "save_unet_half": false,
+  "unet_half": false,
+  "clip_skip": 2,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": true,
+  "debug_arb": false,
+  "save_optimizer": true,
+  "save_states": true,
+  "resume": false,
+  "resume_from": "output/checkpoint_last",
+  "config": null,
+  "arb_dim_limit": 1024,
+  "arb_divisible": 64,
+  "arb_max_ar_error": 4,
+  "arb_max_size": [
+    768,
+    512
+  ],
+  "arb_min_dim": 256,
+  "deepdanbooru": false,
+  "dd_threshold": 0.6,
+  "dd_alpha_sort": false,
+  "dd_use_spaces": true,
+  "dd_use_escape": true,
+  "enable_rotate": false,
+  "dd_include_ranks": false,
+  "use_ema": false,
+  "ucg": 0.0,
+  "debug_prompt": false,
+  "xformers": true
+}

checkpoint_last/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

checkpoint_last/scheduler/scheduler_config.json

@@ -0,0 +1,17 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.15.0.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": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "steps_offset": 1,
+  "thresholding": false,
+  "trained_betas": null
+}

checkpoint_last/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "./model-hf",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "vocab_size": 49408
+}

checkpoint_last/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
+  }
+}

checkpoint_last/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
+  }
+}

checkpoint_last/unet/config.json

@@ -0,0 +1,52 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.15.0.dev0",
+  "_name_or_path": "./model-hf",
+  "act_fn": "silu",
+  "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,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "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_time_scale_shift": "default",
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

checkpoint_last/vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.15.0.dev0",
+  "_name_or_path": "./model-hf",
+  "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"
+  ]
+}