Upload 6 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+teaser_coco.jpg filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,47 @@
+{
+    "_class_name": "UNet2DConditionModel",
+    "_diffusers_version": "0.10.0.dev0",
+    "act_fn": "silu",
+    "attention_head_dim": [
+      5,
+      10,
+      20,
+      20
+    ],
+    "block_out_channels": [
+      320,
+      640,
+      1280,
+      1280
+    ],
+    "center_input_sample": false,
+    "cross_attention_dim": 1024,
+    "down_block_types": [
+      "CrossAttnDownBlock2D",
+      "CrossAttnDownBlock2D",
+      "CrossAttnDownBlock2D",
+      "DownBlock2D"
+    ],
+    "downsample_padding": 1,
+    "dual_cross_attention": false,
+    "flip_sin_to_cos": true,
+    "freq_shift": 0,
+    "in_channels": 4,
+    "layers_per_block": 2,
+    "mid_block_scale_factor": 1,
+    "norm_eps": 1e-05,
+    "norm_num_groups": 32,
+    "num_class_embeds": null,
+    "only_cross_attention": false,
+    "out_channels": 4,
+    "sample_size": 96,
+    "up_block_types": [
+      "UpBlock2D",
+      "CrossAttnUpBlock2D",
+      "CrossAttnUpBlock2D",
+      "CrossAttnUpBlock2D"
+    ],
+    "use_linear_projection": true,
+    "upcast_attention": true
+  }
+  

denoising_unet.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd01b708ec009730808a3d86b19f5a7317bde8e74107385b114b52cca0247f10
+size 3463934162

fusion_layer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab1e96b6c08b13f1afdb332aed2caccc9a7fa10ed8ed1dc149242be500c7ad3
+size 1952

pose_guider.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b12380e446b166f268e917973f7f8dbdda0e47b1fff6da204fb69b97a99112f
+size 2071810

reference_unet.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26de46271d10f192e5f7fcaba2819f2113e7293d1bed3eed1493d5e0761d232f
+size 3463883746