thanks to yisol ❤

text_encoder_2/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8/text_encoder_2",
+  "_name_or_path": "camenduru/IDM-VTON-F16",
   "architectures": [
     "CLIPTextModelWithProjection"
   ],
@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 1280,
   "torch_dtype": "float16",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.40.0",
   "vocab_size": 49408
 }

text_encoder_2/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283bb90f987a133dec11947571aca17692ed32f3fff708441ac8eedcfa4a040e
-size 2778702976
+oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
+size 1389382176