Copy image encoder model from https://huggingface.co/h94/IP-Adapter/tree/5c2eae7d8a9c3365ba4745f16b94eb0293e319d3/models/image_encoder .

README.md

@@ -1,3 +1,5 @@
 ---
 license: apache-2.0
 ---
+
+This model is a copy of https://huggingface.co/h94/IP-Adapter/tree/5c2eae7d8a9c3365ba4745f16b94eb0293e319d3/models/image_encoder. It is hosted here for compatibility with InvokeAI.

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"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ca9667da1ca9e0b0f75e46bb030f7e011f44f86cbfb8d5a36590fcd7507b030
+size 2528373448