correct safetensors

feature_extractor/preprocessor_config.json

@@ -1,8 +1,12 @@
 {
-  "crop_size": 224,
+  "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": [
@@ -10,11 +14,15 @@
     0.4578275,
     0.40821073
   ],
+  "image_processor_type": "CLIPImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,
     0.27577711
   ],
   "resample": 3,
-  "size": 224
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
 }

model_index.json

@@ -1,10 +1,11 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.2.2",
+  "_diffusers_version": "0.12.0.dev0",
   "feature_extractor": [
     "transformers",
-    "CLIPFeatureExtractor"
+    "CLIPImageProcessor"
   ],
+  "requires_safety_checker": true,
   "safety_checker": [
     "stable_diffusion",
     "StableDiffusionSafetyChecker"

safety_checker/config.json

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "./safety_module",
+  "_commit_hash": null,
+  "_name_or_path": "stable-diffusion-v1-4/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],
@@ -13,6 +14,7 @@
     "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,
@@ -60,14 +62,17 @@
     "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,
@@ -75,7 +80,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.21.0.dev0",
+    "transformers_version": "4.25.1",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vocab_size": 49408
@@ -86,7 +91,7 @@
     "num_attention_heads": 12,
     "num_hidden_layers": 12
   },
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": null,
   "vision_config": {
     "_name_or_path": "",
@@ -94,6 +99,7 @@
     "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,
@@ -133,6 +139,7 @@
     "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,
@@ -142,14 +149,17 @@
     "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,
@@ -157,7 +167,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.21.0.dev0",
+    "transformers_version": "4.25.1",
     "typical_p": 1.0,
     "use_bfloat16": false
   },

safety_checker/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4666d0f9b718a6ed165ce95b8aac0d3d78031b8906fdc88ca8e735af5261788c
-size 1215981833
+oid sha256:69c4f8737c7620a738704911a1c7be4dce7bad37bead09e9e499da8810ffb26d
+size 608018446

scheduler/scheduler_config.json

@@ -1,13 +1,14 @@
 {
   "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.7.0.dev0",
+  "_diffusers_version": "0.12.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
+  "clip_sample": false,
   "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
   "set_alpha_to_one": false,
   "skip_prk_steps": true,
   "steps_offset": 1,
-  "trained_betas": null,
-  "clip_sample": false
+  "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
+  "_name_or_path": "stable-diffusion-v1-4/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -18,7 +18,8 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "torch_dtype": "float32",
-  "transformers_version": "4.21.0.dev0",
+  "projection_dim": 512,
+  "torch_dtype": "float16",
+  "transformers_version": "4.25.1",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b3a12df205cb3c74dd4eae4354d93f606ae6b3bc29d5d06fd97921cb9ad8a81
-size 492265879
+oid sha256:fc83cf401d930147807e7c44021c164bcc5508c9d4cc0ff35f4e354685ca9cd0
+size 246144867

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": "stable-diffusion-v1-4/tokenizer",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.2.2",
+  "_diffusers_version": "0.12.0.dev0",
+  "_name_or_path": "stable-diffusion-v1-4/unet",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [
@@ -10,6 +11,7 @@
     1280
   ],
   "center_input_sample": false,
+  "class_embed_type": null,
   "cross_attention_dim": 768,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -18,19 +20,26 @@
     "DownBlock2D"
   ],
   "downsample_padding": 1,
+  "dual_cross_attention": false,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
   "layers_per_block": 2,
   "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
   "out_channels": 4,
+  "resnet_time_scale_shift": "default",
   "sample_size": 64,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
-  ]
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:62d48b4d841a3178511fa453df0dae59b22089ace64609cc9d5353d0a7f37c26
-size 3438354725

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145a07e0f05ec5bbe6e2e9faf608bdb311caf708895cac8c8ed713c59864e1e8
-size 3438167534
+oid sha256:18518e7407ace29645a10ea0d1749ee299b28d1fca584336abbcd16abeba744e
+size 1719125271

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.2.2",
+  "_diffusers_version": "0.12.0.dev0",
+  "_name_or_path": "stable-diffusion-v1-4/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -17,6 +18,7 @@
   "in_channels": 3,
   "latent_channels": 4,
   "layers_per_block": 2,
+  "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 512,
   "up_block_types": [

vae/diffusion_pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1b134cded8eb78b184aefb8805b6b572f36fa77b255c483665dda931fa0130c5
-size 334707217

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b5134f4dbc140d9c11f11cba3233099e00af40f262f136c691fb7d38d2194c
-size 334643276
+oid sha256:11e897bda3163f66848a4abe4613001d27502c985c84d33eb10e7387f9010a2c
+size 167335315