Fix SD2.X clip single file load projection_dim (#10770)

* Fix SD2.X clip single file load projection_dim

Infer projection_dim from the checkpoint before loading
from pretrained, override any incorrect hub config.

Hub configuration for SD2.X specifies projection_dim=512
which is incorrect for SD2.X checkpoints loaded from civitai
and similar.

Exception was previously thrown upon attempting to
load_model_dict_into_meta for SD2.X single file checkpoints.

Such LDM models usually require projection_dim=1024

* convert_open_clip_checkpoint use hidden_size for text_proj_dim

* convert_open_clip_checkpoint, revert checkpoint[text_proj_key].shape[1] -> [0]

values are identical

---------

Co-authored-by: Teriks <[email protected]>
Co-authored-by: Dhruv Nair <[email protected]>

Author: Teriks

src/diffusers/loaders/single_file_utils.py

@@ -1448,8 +1448,8 @@ def convert_open_clip_checkpoint(
 
     if text_proj_key in checkpoint:
         text_proj_dim = int(checkpoint[text_proj_key].shape[0])
-    elif hasattr(text_model.config, "projection_dim"):
-        text_proj_dim = text_model.config.projection_dim
+    elif hasattr(text_model.config, "hidden_size"):
+        text_proj_dim = text_model.config.hidden_size
     else:
         text_proj_dim = LDM_OPEN_CLIP_TEXT_PROJECTION_DIM