thanks to yisol ❤

text_encoder/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",
+  "_name_or_path": "camenduru/IDM-VTON-F16",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float16",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.40.0",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79f531155c765c22c89e23328793a2e91a1178070af961c57e2eae5f0509b65b
-size 492265879
+oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+size 246144152

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.21.0.dev0",
-  "_name_or_path": "madebyollin/sdxl-vae-fp16-fix",
+  "_diffusers_version": "0.25.0",
+  "_name_or_path": "camenduru/IDM-VTON-F16",
   "act_fn": "silu",
   "block_out_channels": [
     128,

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98a14dc6fe8d71c83576f135a87c61a16561c9c080abba418d2cc976ee034f88
-size 334643268
+oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
+size 167335342