AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

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

Browse Source 
* 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 <Teriks@users.noreply.github.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
This commit is contained in:
Teriks
2025-03-03 07:30:39 -06:00
committed by GitHub
parent 5e3b7d2d8a
commit 9e910c4633
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/diffusers/loaders/single_file_utils.py
View File

@@ -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