thanks to yisol ❤

image_encoder/config.json

@@ -1,23 +1,25 @@
 {
-  "_name_or_path": "./image_encoder",
+  "_name_or_path": "camenduru/IDM-VTON-F16",
   "architectures": [
-    "CLIPVisionModelWithProjection"
+    "CLIPTextModelWithProjection"
   ],
   "attention_dropout": 0.0,
+  "bos_token_id": 0,
   "dropout": 0.0,
+  "eos_token_id": 2,
   "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,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
   "num_hidden_layers": 32,
-  "patch_size": 14,
-  "projection_dim": 1024,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
   "torch_dtype": "float16",
-  "transformers_version": "4.28.0.dev0"
+  "transformers_version": "4.40.0",
+  "vocab_size": 49408
 }

image_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca9667da1ca9e0b0f75e46bb030f7e011f44f86cbfb8d5a36590fcd7507b030
-size 2528373448
+oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
+size 1389382176