Delete feature_extractor (#3)

- Delete feature_extractor (0093a49096d43db20d4d12418eb8e3db7937e39a)
- Delete safety_checker (473f6b9c0d4855a43a8e24b4395f7768a97239c5)
- Delete scheduler (d94f333a0eddd6c4839725c742554573f4db5b05)
- Delete text_encoder (f15311b2e78dc9fda91580bffd8d69a6f885fc10)
- Delete tokenizer (275f0b4b381325e9169698c3ddc0a3b41a1fde4d)
- Delete unet (335276ba5a7a19d58057bf2a531ca3080bc1c654)
- Delete vae (c0c229b555f63a93793c2cfd35020d1d9d42cd6d)
- Delete model_index.json (56df33c70b6b9bb595669546f7e2c5280e5dccb5)
- Upload 13 files (f4cef746b3a2b239f03e79e8ac9b3e84658f597c)

args.json

@@ -0,0 +1,80 @@
+{
+  "disable_cudnn_benchmark": true,
+  "use_text_files_as_captions": false,
+  "stop_text_encoder_training": 999999999999999,
+  "use_bucketing": true,
+  "regenerate_latent_cache": false,
+  "save_latents_cache": false,
+  "sample_on_training_start": true,
+  "add_class_images_to_dataset": false,
+  "auto_balance_concept_datasets": false,
+  "sample_aspect_ratios": false,
+  "dataset_repeats": 40,
+  "save_every_n_epoch": 1,
+  "pretrained_model_name_or_path": "F:\\AI\\Software\\DreamboothSimpleUI TESTS\\data\\diffusers\\SD-2.1",
+  "pretrained_vae_name_or_path": "",
+  "tokenizer_name": null,
+  "instance_data_dir": null,
+  "class_data_dir": null,
+  "instance_prompt": null,
+  "class_prompt": null,
+  "save_sample_prompt": null,
+  "n_save_sample": 4,
+  "sample_height": 768,
+  "sample_width": 768,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 30,
+  "with_prior_preservation": false,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 1000,
+  "output_dir": "models/mosaic",
+  "seed": 3434554,
+  "resolution": 768,
+  "center_crop": false,
+  "train_text_encoder": true,
+  "train_batch_size": 4,
+  "sample_batch_size": 4,
+  "num_train_epochs": 6,
+  "max_train_steps": 1680,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 1e-06,
+  "scale_lr": false,
+  "lr_scheduler": "constant",
+  "lr_warmup_steps": 0,
+  "use_8bit_adam": false,
+  "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",
+  "not_cache_latents": false,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "Mosaic Art",
+      "class_prompt": "Artstyle",
+      "instance_data_dir": "F:/AI/Data/Datasets/Captionned/good caption/Mosaic",
+      "class_data_dir": "F:/AI/Data/Datasets/Regularisation/Artstyle",
+      "do_not_balance": 0
+    }
+  ],
+  "save_sample_controlled_seed": null,
+  "delete_checkpoints_when_full_drive": false,
+  "send_telegram_updates": false,
+  "telegram_chat_id": "0",
+  "telegram_token": "0",
+  "use_deepspeed_adam": false,
+  "append_sample_controlled_seed_action": null,
+  "add_sample_prompt": [
+    "Mosaic art"
+  ],
+  "use_image_names_as_captions": true
+}

feature_extractor/preprocessor_config.json

@@ -1,28 +0,0 @@
-{
-  "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

@@ -1,18 +1,18 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.10.0.dev0",
+  "_diffusers_version": "0.10.2",
   "feature_extractor": [
-    "transformers",
-    "CLIPImageProcessor"
+    null,
+    null
   ],
-  "requires_safety_checker": true,
+  "requires_safety_checker": false,
   "safety_checker": [
-    "stable_diffusion",
-    "StableDiffusionSafetyChecker"
+    null,
+    null
   ],
   "scheduler": [
     "diffusers",
-    "PNDMScheduler"
+    "DDIMScheduler"
   ],
   "text_encoder": [
     "transformers",

safety_checker/config.json

@@ -1,181 +0,0 @@
-{
-  "_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
-  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
-  "architectures": [
-    "StableDiffusionSafetyChecker"
-  ],
-  "initializer_factor": 1.0,
-  "logit_scale_init_value": 2.6592,
-  "model_type": "clip",
-  "projection_dim": 768,
-  "text_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 0,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "dropout": 0.0,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 2,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "quick_gelu",
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-05,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 77,
-    "min_length": 0,
-    "model_type": "clip_text_model",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 1,
-    "prefix": null,
-    "problem_type": null,
-    "projection_dim": 512,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "transformers_version": "4.26.0.dev0",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "vocab_size": 49408
-  },
-  "text_config_dict": {
-    "hidden_size": 768,
-    "intermediate_size": 3072,
-    "num_attention_heads": 12,
-    "num_hidden_layers": 12
-  },
-  "torch_dtype": "float32",
-  "transformers_version": null,
-  "vision_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "dropout": 0.0,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "quick_gelu",
-    "hidden_size": 1024,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_size": 224,
-    "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 4096,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-05,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "clip_vision_model",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 16,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_channels": 3,
-    "num_hidden_layers": 24,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "patch_size": 14,
-    "prefix": null,
-    "problem_type": null,
-    "projection_dim": 512,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "transformers_version": "4.26.0.dev0",
-    "typical_p": 1.0,
-    "use_bfloat16": false
-  },
-  "vision_config_dict": {
-    "hidden_size": 1024,
-    "intermediate_size": 4096,
-    "num_attention_heads": 16,
-    "num_hidden_layers": 24,
-    "patch_size": 14
-  }
-}

safety_checker/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
-size 1216064769

scheduler/scheduler_config.json

@@ -1,14 +1,21 @@
 {
-  "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.10.0.dev0",
+  "_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",
+  "prediction_type": "v_prediction",
+  "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

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
+  "_name_or_path": "F:\\AI\\Software\\DreamboothSimpleUI TESTS\\data\\diffusers\\SD-2.1",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -7,19 +7,19 @@
   "bos_token_id": 0,
   "dropout": 0.0,
   "eos_token_id": 2,
-  "hidden_act": "quick_gelu",
-  "hidden_size": 768,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
   "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 77,
   "model_type": "clip_text_model",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
   "pad_token_id": 1,
-  "projection_dim": 768,
+  "projection_dim": 512,
   "torch_dtype": "float32",
-  "transformers_version": "4.26.0.dev0",
+  "transformers_version": "4.25.1",
   "vocab_size": 49408
 }

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b1808fc6f65f5f6f9ea8412d110dc59f93cf6c6d5a41fc9aea987cfc41fafac
-size 492307041
+oid sha256:aed483ba4fb3e2da2c29a257ab6b4c683ac0accd56d77ed5b1df816808aeb292
+size 1361677143

tokenizer/special_tokens_map.json

@@ -13,7 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": "!",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "openai/clip-vit-large-patch14",
+  "name_or_path": "F:\\AI\\Software\\DreamboothSimpleUI TESTS\\data\\diffusers\\SD-2.1\\tokenizer",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,8 +1,14 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.10.0.dev0",
+  "_diffusers_version": "0.10.2",
+  "_name_or_path": "F:\\AI\\Software\\DreamboothSimpleUI TESTS\\data\\diffusers\\SD-2.1",
   "act_fn": "silu",
-  "attention_head_dim": 8,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
   "block_out_channels": [
     320,
     640,
@@ -10,7 +16,7 @@
     1280
   ],
   "center_input_sample": false,
-  "cross_attention_dim": 768,
+  "cross_attention_dim": 1024,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -29,12 +35,13 @@
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
-  "sample_size": 64,
+  "sample_size": 96,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "use_linear_projection": false
+  "upcast_attention": true,
+  "use_linear_projection": true
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13c8d29ed3cb16d19c81c953ad4c3906928c5e4837d69595cfa47b5d9dce2c22
-size 3438366373
+oid sha256:01ebea392218fe6b1b70c9bb37c90ccce17d342e6bd745641d7ca650af1de7f6
+size 3463923045

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.10.0.dev0",
+  "_diffusers_version": "0.10.2",
+  "_name_or_path": "F:\\AI\\Software\\DreamboothSimpleUI TESTS\\data\\diffusers\\SD-2.1",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -19,7 +20,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 512,
+  "sample_size": 768,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf4507d99b88db73f3916e2a20169fe74ada6b5582e9af56cfa80f5f3141765
-size 334711857
+oid sha256:1b4889b6b1d4ce7ae320a02dedaeff1780ad77d415ea0d744b476155c6377ddc
+size 334707217