Adding `diffusers` weights of this model

feature_extractor/preprocessor_config.json

@@ -1,4 +1,21 @@
 {
+  "_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
@@ -8,7 +25,6 @@
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,
-  "feature_extractor_type": "CLIPFeatureExtractor",
   "image_mean": [
     0.48145466,
     0.4578275,

model_index.json

@@ -1,13 +1,22 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.18.0.dev0",
+  "_diffusers_version": "0.28.0.dev0",
   "feature_extractor": [
     "transformers",
     "CLIPFeatureExtractor"
   ],
+  "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": "float32",
+  "transformers_version": "4.41.1",
+  "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:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
+size 1215979664

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": "0.28.0.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

@@ -15,10 +15,10 @@
   "max_position_embeddings": 77,
   "model_type": "clip_text_model",
   "num_attention_heads": 12,
-  "num_hidden_layers": 11,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
-  "torch_dtype": "float16",
-  "transformers_version": "4.34.0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
   "vocab_size": 49408
 }

text_encoder/model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd6bf712394b8e55be64aa94c98696ffcda6104b002d5f1a43e6c3c87850798
-size 246144152
+oid sha256:e6e7fb6d6df84e4c08b42c3bde820b9f255e2e0765dfb457d06e32cc050674b3
+size 492265168

tokenizer/special_tokens_map.json

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<|startoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer/tokenizer_config.json

@@ -7,7 +7,7 @@
       "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "49407": {
       "content": "<|endoftext|>",
@@ -15,10 +15,9 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
-  "additional_special_tokens": [],
   "bos_token": "<|startoftext|>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
@@ -27,6 +26,5 @@
   "model_max_length": 77,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "CLIPTokenizer",
-  "tokenizer_file": "/home/user/.cache/huggingface/hub/models--openai--clip-vit-large-patch14/snapshots/32bd64288804d66eefd0ccbe215aa642df71cc41/tokenizer.json",
   "unk_token": "<|endoftext|>"
 }

unet/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.22.0.dev0",
+  "_diffusers_version": "0.28.0.dev0",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
@@ -48,6 +48,7 @@
   "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,

unet/diffusion_pytorch_model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948239ec8b8013576b22617fcff84ad0b25b8f2ee49b3a7f30942f31fa09f65f
-size 1719125304
+oid sha256:847175e742c45881597d96887aadad7955cfc6215bbcb72773b224b1f3a8e7f4
+size 3438167536

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.22.0.dev0",
+  "_diffusers_version": "0.28.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -17,6 +17,8 @@
   "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,

vae/diffusion_pytorch_model.fp16.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180d20a23805d84438d4af2a4c67b118d790cd991f2315f2e5c0c22f150757ba
-size 167335342
+oid sha256:875de58d4301af796fc03a905e1934fa662e3d0fd9f02e05412c8dba8d416512
+size 334643268