fix more

unet/my_unet_model.py

@@ -34,7 +34,7 @@ from diffusers.models.embeddings import (
     ImageHintTimeEmbedding,
     ImageProjection,
     ImageTimeEmbedding,
-    PositionNet,
+    GLIGENTextBoundingboxProjection,
     TextImageProjection,
     TextImageTimeEmbedding,
     TextTimeEmbedding,
@@ -42,7 +42,7 @@ from diffusers.models.embeddings import (
     Timesteps,
 )
 from diffusers.models.modeling_utils import ModelMixin
-from diffusers.models.unet_2d_blocks import (
+from diffusers.models.unets.unet_2d_blocks import (
     UNetMidBlock2DCrossAttn,
     UNetMidBlock2DSimpleCrossAttn,
     get_down_block,
@@ -586,7 +586,7 @@ class MyUNetModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin):
                 positive_len = cross_attention_dim[0]
 
             feature_type = "text-only" if attention_type == "gated" else "text-image"
-            self.position_net = PositionNet(
+            self.position_net = GLIGENTextBoundingboxProjection(
                 positive_len=positive_len, out_dim=cross_attention_dim, feature_type=feature_type
             )