Upload StableDiffusionXLPipeline

README.md

@@ -1,10 +1,11 @@
 ---
+library_name: diffusers
 license: creativeml-openrail-m
 tags:
-  - modelslab.com
-  - stable-diffusion-api
-  - text-to-image
-  - ultra-realistic
+- modelslab.com
+- stable-diffusion-api
+- text-to-image
+- ultra-realistic
 pinned: true
 ---
 

model_index.json

@@ -1,19 +1,15 @@
 {
-  "_class_name": "StableDiffusionPipeline",
+  "_class_name": "StableDiffusionXLPipeline",
   "_diffusers_version": "0.29.0.dev0",
   "feature_extractor": [
     null,
     null
   ],
+  "force_zeros_for_empty_prompt": true,
   "image_encoder": [
     null,
     null
   ],
-  "requires_safety_checker": true,
-  "safety_checker": [
-    null,
-    null
-  ],
   "scheduler": [
     "diffusers",
     "EulerDiscreteScheduler"
@@ -22,10 +18,18 @@
     "transformers",
     "CLIPTextModel"
   ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
   "tokenizer": [
     "transformers",
     "CLIPTokenizer"
   ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
   "unet": [
     "diffusers",
     "UNet2DConditionModel"

text_encoder_2/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "vocab_size": 49408
+}

text_encoder_2/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60e6af871df3870ce5dc7f1720e158f2f27806ad5ee50fb12d92c418d7ce5647
+size 1389382176

tokenizer_2/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_2/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}