End of training

800_lora.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce236e95751241d20b3bfe3efebb874e71c285ddf29309ba2433a13c0b25c34d
+size 477514

feature_extractor/preprocessor_config.json

@@ -0,0 +1,44 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "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

@@ -1,23 +1,23 @@
 {
   "_class_name": "StableDiffusionPipeline",
   "_diffusers_version": "0.27.2",
-  "_name_or_path": "SG161222/Realistic_Vision_V4.0",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
   "feature_extractor": [
-    null,
-    null
+    "transformers",
+    "CLIPImageProcessor"
   ],
   "image_encoder": [
     null,
     null
   ],
-  "requires_safety_checker": null,
+  "requires_safety_checker": false,
   "safety_checker": [
     null,
     null
   ],
   "scheduler": [
     "diffusers",
-    "DEISMultistepScheduler"
+    "DDIMScheduler"
   ],
   "text_encoder": [
     "transformers",

scheduler/scheduler_config.json

@@ -1,23 +1,20 @@
 {
-  "_class_name": "DEISMultistepScheduler",
+  "_class_name": "DDIMScheduler",
   "_diffusers_version": "0.27.2",
-  "algorithm_type": "deis",
   "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,
-  "lower_order_final": true,
   "num_train_timesteps": 1000,
-  "prediction_type": "epsilon",
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": false,
   "sample_max_value": 1.0,
   "set_alpha_to_one": false,
-  "solver_order": 2,
-  "solver_type": "logrho",
+  "skip_prk_steps": true,
   "steps_offset": 1,
   "thresholding": false,
-  "timestep_spacing": "linspace",
-  "trained_betas": null,
-  "use_karras_sigmas": false
+  "timestep_spacing": "leading",
+  "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "SG161222/Realistic_Vision_V4.0",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -7,18 +7,18 @@
   "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": "bfloat16",
   "transformers_version": "4.39.0",
   "vocab_size": 49408

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6de458ec6492039bb381fb8cc8d571ae4885faccde97ef671686d42dc789085e
-size 246144352
+oid sha256:305b018799a2e1dba83e9db17654309814ff4212e40b8096b237ce2e3794a132
+size 680820760

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

@@ -1,6 +1,14 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
     "49406": {
       "content": "<|startoftext|>",
       "lstrip": false,
@@ -24,7 +32,7 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 77,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "!",
   "tokenizer_class": "CLIPTokenizer",
   "unk_token": "<|endoftext|>"
 }

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.27.2",
-  "_name_or_path": "SG161222/Realistic_Vision_V4.0",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -23,7 +23,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 512,
+  "sample_size": 768,
   "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:991a6bec3312d5771f921c5ff3b1d225ae4c1bc9ac24f4b9087e86df0ee6136d
+oid sha256:8d0c34f57abe50f323040f2366c8e22b941068dcdf53c8eb1d6fafb838afecb7
 size 167335590