Adding `diffusers` weights of this model (#3)

- Adding `diffusers` weights of this model (5ac9ad2fd8a9066d9c1bfb02708ccf60561995ed)

feature_extractor/preprocessor_config.json

@@ -24,5 +24,6 @@
   "rescale_factor": 0.00392156862745098,
   "size": {
     "shortest_edge": 224
-  }
+  },
+  "use_square_size": false
 }

model_index.json

@@ -1,18 +1,22 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.18.0.dev0",
+  "_diffusers_version": "0.25.0.dev0",
   "feature_extractor": [
     "transformers",
     "CLIPFeatureExtractor"
   ],
-  "requires_safety_checker": null,
-  "safety_checker": [
+  "image_encoder": [
     null,
     null
   ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
   "scheduler": [
     "diffusers",
-    "DDIMScheduler"
+    "PNDMScheduler"
   ],
   "text_encoder": [
     "transformers",

safety_checker/config.json

@@ -0,0 +1,28 @@
+{
+  "_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": {
+    "dropout": 0.0,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
+  }
+}

safety_checker/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ecdfa243b170f9b4cb3eefaf0f64552ef78fc0bf0eb1c5b9675308447184f6
+size 608016280

safety_checker/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
+size 1215979664

scheduler/scheduler_config.json

@@ -1,19 +1,15 @@
 {
-  "_class_name": "DDIMScheduler",
-  "_diffusers_version": "0.18.0.dev0",
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.25.0.dev0",
   "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,
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
-  "rescale_betas_zero_snr": false,
-  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
+  "skip_prk_steps": true,
   "steps_offset": 1,
-  "thresholding": false,
   "timestep_spacing": "leading",
   "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -20,6 +19,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float16",
-  "transformers_version": "4.30.2",
+  "transformers_version": "4.35.2",
   "vocab_size": 49408
 }

text_encoder/model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:313a5f245425ca3d5b10bad076487fa50072ab51840c18ff6b31b3ed7bb646cd
-size 246144864
+oid sha256:65283769869898538ada6619abf421e4dacf2ab51b026bb4b6486dec25701492
+size 246144152

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ddbc7520c24ca4baf40f808ccfa03b87c3adf5ca751f9619cf8229829279ae9
-size 492265880
+oid sha256:3028cd4b1259b094ed818903eb61140aa24063b3abdbb2b2c93828d6edaffc3f
+size 492265168

tokenizer/special_tokens_map.json

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

tokenizer/tokenizer_config.json

@@ -1,33 +1,30 @@
 {
   "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",
   "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

@@ -1,10 +1,12 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.18.0.dev0",
+  "_diffusers_version": "0.25.0.dev0",
   "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,
@@ -25,6 +27,7 @@
     "DownBlock2D"
   ],
   "downsample_padding": 1,
+  "dropout": 0.0,
   "dual_cross_attention": false,
   "encoder_hid_dim": null,
   "encoder_hid_dim_type": null,
@@ -45,12 +48,14 @@
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
   "sample_size": 96,
   "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": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.18.0.dev0",
+  "_diffusers_version": "0.25.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -14,6 +14,7 @@
     "DownEncoderBlock2D",
     "DownEncoderBlock2D"
   ],
+  "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
   "layers_per_block": 2,

vae/diffusion_pytorch_model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b443aac6bdaeafd5fc30c0d24b601582f4a6120b9ea0381bdcd7c6a12ab95b
+oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
 size 167335342

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceee6a41c890c9e2732241f291c371c196c478576461c63066961841f2c8962a
+oid sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
 size 334643268