Skip to content

Fix path generation in IP Adapter #6564

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sayakpaul merged 7 commits into from
Jan 16, 2024
Merged

Fix path generation in IP Adapter #6564

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
ec8c961
Fix path generation on Windows
fabiorigano Jan 13, 2024
5ceba27
Update set_default_attn_processors
fabiorigano Jan 13, 2024
8241a01
Use pathlib
fabiorigano Jan 13, 2024
07857be
Fix quality
fabiorigano Jan 13, 2024
c6de071
Fix copy
fabiorigano Jan 13, 2024
1e74b2a
Revert changes in set_default_attn_processors
fabiorigano Jan 15, 2024
de6000f
Merge branch 'main' into ipadapterfixes
sayakpaul Jan 16, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/diffusers/loaders/ip_adapter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
from pathlib import Path
from typing import Dict, Union

import torch
Expand Down Expand Up @@ -138,7 +138,7 @@ def load_ip_adapter(
logger.info(f"loading image_encoder from {pretrained_model_name_or_path_or_dict}")
image_encoder = CLIPVisionModelWithProjection.from_pretrained(
pretrained_model_name_or_path_or_dict,
subfolder=os.path.join(subfolder, "image_encoder"),
subfolder=Path(subfolder, "image_encoder").as_posix(),
Copy link
Member

@sayakpaul sayakpaul Jan 15, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It seems to be a good idea to follow this throughout in the library to better support Windows.

What say @patrickvonplaten @yiyixuxu?

Copy link
Member

@sayakpaul sayakpaul Jan 16, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Opened a tracker here: #6585.

).to(self.device, dtype=self.dtype)
self.image_encoder = image_encoder
self.register_to_config(image_encoder=["transformers", "CLIPVisionModelWithProjection"])
Expand Down