-
Notifications
You must be signed in to change notification settings - Fork 455
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.
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
add vae image processor #1219
add vae image processor #1219
Conversation
The documentation is not available anymore as the PR was closed or merged. |
@@ -29,6 +29,7 @@ jobs: | |||
python-version: ${{ matrix.python-version }} | |||
- name: Install dependencies | |||
run: | | |||
pip install git+https://github.com/huggingface/diffusers |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
waiting for diffusers
next release before we can merge
edit : now comaptible
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
# additional invisible-watermark dependency for SD XL | ||
from ..pipelines.diffusers.watermark import StableDiffusionXLWatermarker | ||
if add_watermarker: | ||
from ..pipelines.diffusers.watermark import StableDiffusionXLWatermarker |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Could this import be at the top of the file?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
No without making invisible-watermark
a hard dependency, I added an additional verification in dd292d8 to check that invisible-watermark
is installed if needed
In this PR we add an
VaeImageProcessor
class enabling the preprocessing and postprocessing of images pipelines, in which we correctly reshape the inputs as expected by the ONNX model. The watermark is also made optional.