add test

image_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "./image_encoder",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
+  "projection_dim": 1024,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0.dev0"
+}

image_processor/preprocessor_config.json

@@ -0,0 +1,4 @@
+{
+    "feature_extractor_type": "CLIPFeatureExtractor",
+    "image_processor_type": "CLIPImageProcessor"
+  }

image_projection/config.json

@@ -0,0 +1,9 @@
+{
+    "architectures": [
+      "ImageProjModel"
+    ],
+    "cross_attention_dim": 768,
+    "clip_embeddings_dim": 1024,
+    "clip_extra_context_tokens": 4
+  }
+  

model_index.json

@@ -0,0 +1,16 @@
+{
+    "_class_name": "IPAdapterPipeline",
+    "_diffusers_version": "0.21.0.dev0",
+    "feature_extractor": [
+      "transformers",
+      "CLIPImageProcessor"
+    ],
+    "image_encoder": [
+      "transformers",
+      "CLIPVisionModelWithProjection"
+    ],
+    "image_projection": [
+        "ip_adapter",
+        "ImageProjModel"
+    ]
+  }