First model version

args.json

@@ -0,0 +1,99 @@
+{
+  "pretrained_model_name_or_path": "./stable-diffusion-v1-5",
+  "pretrained_vae_name_or_path": null,
+  "tokenizer_name": null,
+  "instance_data_dir": "./instance-images",
+  "class_data_dir": "./class-images",
+  "instance_prompt": "masterpiece, best quality, (clean background), (simple background), (architecture), (solo), 3D object, Stereoscopic feeling, lyj_window_module",
+  "class_prompt": "masterpiece, best quality, (clean background), (simple background), (architecture), (solo), 3D object, Stereoscopic feeling",
+  "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, (clean background), (simple background), (architecture), (solo), 3D object, Stereoscopic feeling",
+  "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": true,
+  "pad_tokens": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 35,
+  "output_dir": "./output",
+  "seed": 1337,
+  "resolution": 512,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 2,
+  "max_train_steps": 3000,
+  "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": 500,
+  "save_min_steps": 10,
+  "mixed_precision": "fp16",
+  "not_cache_latents": false,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "masterpiece, best quality, (clean background), (simple background), (architecture), (solo), 3D object, Stereoscopic feeling, lyj_window_module",
+      "class_prompt": "masterpiece, best quality, (clean background), (simple background), (architecture), (solo), 3D object, Stereoscopic feeling",
+      "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": 1,
+  "num_cycles": 1,
+  "last_epoch": -1,
+  "use_aspect_ratio_bucket": false,
+  "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": false
+}

feature_extractor/preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

model_index.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.8.0.dev0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPFeatureExtractor"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.8.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "set_alpha_to_one": false,
+  "steps_offset": 1,
+  "trained_betas": null
+}

state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5b25fadcc1deebbec71ef576343799507980e4c7b4f68e2c8254298e0c8575
+size 1725045466

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "./stable-diffusion-v1-5",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98124f3d5663b2f14ff08d4c29db93800622b4fcfa3d952bb6f9112f5d6dadd7
+size 492307041

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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,
+  "name_or_path": "./stable-diffusion-v1-5/tokenizer",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,37 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.8.0.dev0",
+  "_name_or_path": "./stable-diffusion-v1-5",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "out_channels": 4,
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ]
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f524713bed302cf5b97a3e1b28698b1b2f30839c89baa4a92b48fa02ff8933f
+size 3438375973

vae/config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.8.0.dev0",
+  "_name_or_path": "./stable-diffusion-v1-5",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af27ea858349760ebe3311953e0bfe8d6fd257dc9537ae0b2b938c262132a2c6
+size 334711857