Convert model to Safetensors format and optimize structure

model_index.json

@@ -1,11 +1,15 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.19.0.dev0",
-  "_name_or_path": "SG161222/Realistic_Vision_V4.0",
+  "_diffusers_version": "0.35.2",
+  "_name_or_path": "HyHorX/realistic-diffusion-v1",
   "feature_extractor": [
     null,
     null
   ],
+  "image_encoder": [
+    null,
+    null
+  ],
   "requires_safety_checker": false,
   "safety_checker": [
     null,

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "DPMSolverMultistepScheduler",
-  "_diffusers_version": "0.19.0.dev0",
+  "_diffusers_version": "0.35.2",
   "algorithm_type": "dpmsolver++",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
@@ -8,18 +8,28 @@
   "clip_sample": false,
   "clip_sample_range": 1.0,
   "dynamic_thresholding_ratio": 0.995,
+  "euler_at_final": false,
+  "final_sigmas_type": "zero",
+  "flow_shift": 1.0,
   "lambda_min_clipped": -Infinity,
   "lower_order_final": true,
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
   "sample_max_value": 1.0,
   "set_alpha_to_one": false,
   "solver_order": 2,
   "solver_type": "midpoint",
   "steps_offset": 1,
   "thresholding": false,
+  "time_shift_type": "exponential",
   "timestep_spacing": "linspace",
   "trained_betas": null,
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_flow_sigmas": false,
   "use_karras_sigmas": false,
+  "use_lu_lambdas": false,
   "variance_type": null
 }

text_encoder/config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--SG161222--Realistic_Vision_V4.0/snapshots/c2ce281f57e54220379e82482708ea925f10770f/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "dropout": 0.0,
+  "dtype": "float16",
   "eos_token_id": 2,
   "hidden_act": "quick_gelu",
   "hidden_size": 768,
@@ -19,7 +19,6 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
-  "torch_dtype": "float16",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.57.1",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd56d54a36ac54c1de9a247a681059d19751e3706817a09e8b7a75c67ae93584
+size 246144152

tokenizer/tokenizer_config.json

@@ -1,33 +1,31 @@
 {
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<|startoftext|>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "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
-  }
+  "unk_token": "<|endoftext|>"
 }

unet/config.json

@@ -1,33 +1,65 @@
 {
-    "_class_name": "UNet2DConditionModel",
-    "_diffusers_version": "0.6.0",
-    "act_fn": "silu",
-    "attention_head_dim": 8,
-    "block_out_channels": [
-      320,
-      640,
-      1280
-    ],
-    "center_input_sample": false,
-    "cross_attention_dim": 768,
-    "down_block_types": [
-      "CrossAttnDownBlock2D",
-      "CrossAttnDownBlock2D",
-      "CrossAttnDownBlock2D"
-    ],
-    "downsample_padding": 1,
-    "flip_sin_to_cos": true,
-    "freq_shift": 0,
-    "in_channels": 4,
-    "layers_per_block": 1,
-    "mid_block_type": null,
-    "norm_eps": 1e-05,
-    "norm_num_groups": 32,
-    "out_channels": 4,
-    "sample_size": 64,
-    "up_block_types": [
-      "CrossAttnUpBlock2D",
-      "CrossAttnUpBlock2D",
-      "CrossAttnUpBlock2D"
-    ]
-  }
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.35.2",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--HyHorX--realistic-diffusion-v1/snapshots/b67ee59f81f4bbfc2ea7587b244e98b16d40f2dd/unet",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    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,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 1,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": null,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "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 sha256:7a42d33f11664e625855aa437dd5aa5dabed711b54d55eb92d5e027db1c04196
+size 646813304

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.19.0.dev0",
-  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--SG161222--Realistic_Vision_V4.0/snapshots/c2ce281f57e54220379e82482708ea925f10770f/vae",
+  "_diffusers_version": "0.35.2",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--HyHorX--realistic-diffusion-v1/snapshots/b67ee59f81f4bbfc2ea7587b244e98b16d40f2dd/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -18,15 +18,21 @@
   "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
   "layers_per_block": 2,
+  "mid_block_add_attention": true,
   "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 512,
   "scaling_factor": 0.18215,
+  "shift_factor": null,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",
     "UpDecoderBlock2D"
-  ]
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
 }

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249bd6adf5e03a78cfbc21c689b08f9e285fa49fa81f2cf9ff175c6272a2740a
+size 167335342