fix: 修复 text_encoder_projection_dim 的问题

utils.py

@@ -285,10 +285,13 @@ def call(
         # 7. Prepare added time ids & embeddings
         add_text_embeds = pooled_prompt_embeds
         # 确保 text_encoder_projection_dim 被正确初始化
-        if not hasattr(self, 'text_encoder_projection_dim'):
-            self.text_encoder_projection_dim = 128  # 或者其他适当的默认值
+        if self.text_encoder_2 is None:
+            text_encoder_projection_dim = int(pooled_prompt_embeds.shape[-1])
+        else:
+            text_encoder_projection_dim = self.text_encoder_2.config.projection_dim
         add_time_ids = self._get_add_time_ids(
-            original_size, crops_coords_top_left, target_size, dtype=prompt_embeds.dtype
+            original_size, crops_coords_top_left, target_size, dtype=prompt_embeds.dtype,
+            text_encoder_projection_dim=text_encoder_projection_dim
         )
         if negative_original_size is not None and negative_target_size is not None:
             negative_add_time_ids = self._get_add_time_ids(
@@ -296,6 +299,7 @@ def call(
                 negative_crops_coords_top_left,
                 negative_target_size,
                 dtype=prompt_embeds.dtype,
+                text_encoder_projection_dim=text_encoder_projection_dim
             )
         else:
             negative_add_time_ids = add_time_ids