Upload with huggingface_hub

args.json

@@ -0,0 +1,104 @@
+{
+  "shuffle_per_epoch": false,
+  "attention": "xformers",
+  "model_variant": "base",
+  "aspect_mode": "dynamic",
+  "aspect_mode_action_preference": "add",
+  "use_ema": true,
+  "clip_penultimate": false,
+  "conditional_dropout": null,
+  "disable_cudnn_benchmark": true,
+  "use_text_files_as_captions": false,
+  "sample_from_batch": 0,
+  "stop_text_encoder_training": 999999999999999,
+  "use_bucketing": true,
+  "regenerate_latent_cache": true,
+  "sample_on_training_start": true,
+  "add_class_images_to_dataset": false,
+  "auto_balance_concept_datasets": false,
+  "sample_aspect_ratios": false,
+  "dataset_repeats": 1,
+  "save_every_n_epoch": 5,
+  "pretrained_model_name_or_path": "mekrod/vmp1",
+  "pretrained_vae_name_or_path": "input_vae_model/VAE",
+  "tokenizer_name": null,
+  "instance_data_dir": null,
+  "class_data_dir": null,
+  "instance_prompt": null,
+  "class_prompt": null,
+  "save_sample_prompt": null,
+  "n_save_sample": 1,
+  "sample_height": 512,
+  "sample_width": 512,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 30,
+  "with_prior_preservation": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 206,
+  "output_dir": "output/vmp1e",
+  "seed": 3534554,
+  "resolution": 512,
+  "center_crop": false,
+  "train_text_encoder": false,
+  "train_batch_size": 1,
+  "sample_batch_size": 4,
+  "num_train_epochs": 20,
+  "max_train_steps": 1140,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 1e-06,
+  "scale_lr": false,
+  "lr_scheduler": "constant",
+  "lr_warmup_steps": 0,
+  "use_8bit_adam": true,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_weight_decay": 0.01,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "push_to_hub": false,
+  "hub_token": null,
+  "hub_model_id": null,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "sample_step_interval": 500,
+  "mixed_precision": "fp16",
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "Magali Villeneuve",
+      "instance_data_dir": "datasets/Magali Villeneuve",
+      "class_prompt": "",
+      "class_data_dir": "",
+      "do_not_balance": 0,
+      "use_sub_dirs": 0
+    },
+    {
+      "instance_prompt": "Bo Chen",
+      "instance_data_dir": "datasets/Bo Chen",
+      "class_prompt": "",
+      "class_data_dir": "",
+      "do_not_balance": 0,
+      "use_sub_dirs": 0
+    },
+    {
+      "instance_prompt": "Chengwei Pan",
+      "instance_data_dir": "datasets/Chengwei Pan",
+      "class_prompt": "",
+      "class_data_dir": "",
+      "do_not_balance": 0,
+      "use_sub_dirs": 0
+    }
+  ],
+  "save_sample_controlled_seed": null,
+  "detect_full_drive": true,
+  "send_telegram_updates": false,
+  "telegram_chat_id": "0",
+  "telegram_token": "0",
+  "use_deepspeed_adam": false,
+  "append_sample_controlled_seed_action": null,
+  "add_sample_prompt": null,
+  "use_image_names_as_captions": true,
+  "mask_prompts": null,
+  "batch_tokens": null
+}

feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.10.2",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,21 @@
+{
+  "_class_name": "DPMSolverMultistepScheduler",
+  "_diffusers_version": "0.10.2",
+  "algorithm_type": "dpmsolver++",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "dynamic_thresholding_ratio": 0.995,
+  "lower_order_final": true,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "solver_order": 2,
+  "solver_type": "midpoint",
+  "steps_offset": 1,
+  "thresholding": false,
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "mekrod/vmp1",
+  "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": "4.25.1",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd12d8b6f52dd17cfd35baf3c5c1f229467ba930658b80301668707b74a042f5
+size 492265879

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": "/root/.cache/huggingface/diffusers/models--mekrod--vmp1/snapshots/6d5743b2b92916b33a6aec071ca54ff8f0b6cd09/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 +1,45 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.10.2",
+  "_name_or_path": "mekrod/vmp1",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "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,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:844745538984fdda1e2397c6be09f90eb444cbcacaceeea1b0bf844fae3c0d84
+size 3438167503

vae/config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.10.2",
+  "_name_or_path": "input_vae_model/VAE",
+  "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": 768,
+  "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:beac981a8939a0430dd9b71027125d6abe863f8667f0d8497b9e2f6aa9a1db80
+size 334643245