Skip to content

Set LANCZOS as the default interpolation for image resizing in ControlNet training #11449

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
merged 1 commit into from
Apr 29, 2025
+15 −2
Merged

Set LANCZOS as the default interpolation for image resizing in ControlNet training #11449

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
17 changes: 15 additions & 2 deletions examples/controlnet/train_controlnet_flux.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -639,6 +639,15 @@ def parse_args(input_args=None):
action="store_true",
help="Enable model cpu offload and save memory.",
)
parser.add_argument(
"--image_interpolation_mode",
type=str,
default="lanczos",
choices=[
f.lower() for f in dir(transforms.InterpolationMode) if not f.startswith("__") and not f.endswith("__")
],
help="The image interpolation method to use for resizing images.",
)

if input_args is not None:
args = parser.parse_args(input_args)
Expand Down Expand Up @@ -736,9 +745,13 @@ def get_train_dataset(args, accelerator):


def prepare_train_dataset(dataset, accelerator):
interpolation = getattr(transforms.InterpolationMode, args.image_interpolation_mode.upper(), None)
if interpolation is None:
raise ValueError(f"Unsupported interpolation mode {interpolation=}.")

image_transforms = transforms.Compose(
[
transforms.Resize(args.resolution, interpolation=transforms.InterpolationMode.BILINEAR),
transforms.Resize(args.resolution, interpolation=interpolation),
transforms.CenterCrop(args.resolution),
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5]),
Expand All @@ -747,7 +760,7 @@ def prepare_train_dataset(dataset, accelerator):

conditioning_image_transforms = transforms.Compose(
[
transforms.Resize(args.resolution, interpolation=transforms.InterpolationMode.BILINEAR),
transforms.Resize(args.resolution, interpolation=interpolation),
transforms.CenterCrop(args.resolution),
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5]),
Expand Down
Loading