fix

feature_extractor/preprocessor_config.json

@@ -1,20 +0,0 @@
-{
-  "crop_size": 224,
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_resize": true,
-  "feature_extractor_type": "CLIPFeatureExtractor",
-  "image_mean": [
-    0.48145466,
-    0.4578275,
-    0.40821073
-  ],
-  "image_std": [
-    0.26862954,
-    0.26130258,
-    0.27577711
-  ],
-  "resample": 3,
-  "size": 224
-}

scheduler/scheduler_config.json

@@ -1,14 +1,13 @@
 {
-  "_class_name": "DDIMScheduler",
-  "_diffusers_version": "0.9.0.dev0",
-  "beta_end": 0.02,
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.7.0.dev0",
+  "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
-  "beta_start": 0.0001,
-  "clip_sample": false,
+  "beta_start": 0.00085,
   "num_train_timesteps": 1000,
-  "prediction_type": "v_prediction",
   "set_alpha_to_one": false,
   "skip_prk_steps": true,
   "steps_offset": 1,
-  "trained_betas": null
+  "trained_betas": null,
+  "clip_sample": false
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "hf-models/stable-diffusion-x4-upscaler/text_encoder",
+  "_name_or_path": "openai/clip-vit-large-patch14",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -7,19 +7,18 @@
   "bos_token_id": 0,
   "dropout": 0.0,
   "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_size": 1024,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
   "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 77,
   "model_type": "clip_text_model",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 23,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "projection_dim": 512,
   "torch_dtype": "float32",
-  "transformers_version": "4.25.0.dev0",
+  "transformers_version": "4.21.0.dev0",
   "vocab_size": 49408
 }

text_encoder/model.fp16.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:681c555376658c81dc273f2d737a2aeb23ddb6d1d8e5b3a7064636d359a22668
-size 680821096

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cce6febb0b6d876ee5eb24af35e27e764eb4f9b1d0b7c026c8c3333d4cfc916c
-size 1361597018
+oid sha256:7b3a12df205cb3c74dd4eae4354d93f606ae6b3bc29d5d06fd97921cb9ad8a81
+size 492265879

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2188379b05015f531d61503e714234d00a64939792f3098b324e516547f0194f
-size 1361674657
+oid sha256:770a47a9ffdcfda0b05506a7888ed714d06131d60267e6cf52765d61cf59fd67
+size 492305335

text_encoder/pytorch_model.fp16.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7bb11b1da63986aaaaefb5ef2100d34109c024ac640cacd9ed697150c1c57f01
-size 680900852

tokenizer/special_tokens_map.json

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

tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "hf-models/stable-diffusion-x4-upscaler/tokenizer",
+  "name_or_path": "openai/clip-vit-large-patch14",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",