thanks to yisol ❤

unet_encoder/config.json

@@ -1,7 +1,9 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.19.0.dev0",
+  "_diffusers_version": "0.25.0",
+  "_name_or_path": "camenduru/IDM-VTON-F16",
   "act_fn": "silu",
+  "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
   "addition_time_embed_dim": 256,
   "attention_head_dim": [
@@ -9,6 +11,7 @@
     10,
     20
   ],
+  "attention_type": "default",
   "block_out_channels": [
     320,
     640,
@@ -27,6 +30,7 @@
     "CrossAttnDownBlock2D"
   ],
   "downsample_padding": 1,
+  "dropout": 0.0,
   "dual_cross_attention": false,
   "encoder_hid_dim": null,
   "encoder_hid_dim_type": null,
@@ -47,6 +51,7 @@
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
   "sample_size": 128,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,

unet_encoder/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:357650fbfb3c7b4d94c1f5fd7664da819ad1ff5a839430484b4ec422d03f710a
-size 10270077736
+oid sha256:b679d0fb8cda74b6de62ec3645abe78d814ff9253843735845b5437ed21f1f13
+size 5124658400