Merge branch 'huggingface:main' into aspect_ratio_bucketing

Author: linoytsaban

examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py

@@ -770,6 +770,15 @@ def parse_args(input_args=None):
         ),
     )
     parser.add_argument("--local_rank", type=int, default=-1, help="For distributed training: local_rank")
+    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)
@@ -1034,7 +1043,10 @@ def __init__(
             self.instance_images.extend(itertools.repeat(img, repeats))
 
         self.pixel_values = []
-        train_resize = transforms.Resize(size, interpolation=transforms.InterpolationMode.BILINEAR)
+        interpolation = getattr(transforms.InterpolationMode, args.image_interpolation_mode.upper(), None)
+        if interpolation is None:
+            raise ValueError(f"Unsupported interpolation mode {interpolation=}.")
+        train_resize = transforms.Resize(size, interpolation=interpolation)
         train_crop = transforms.CenterCrop(size) if center_crop else transforms.RandomCrop(size)
         train_flip = transforms.RandomHorizontalFlip(p=1.0)
         train_transforms = transforms.Compose(
@@ -1078,7 +1090,7 @@ def __init__(
 
         self.image_transforms = transforms.Compose(
             [
-                transforms.Resize(size, interpolation=transforms.InterpolationMode.BILINEAR),
+                transforms.Resize(size, interpolation=interpolation),
                 transforms.CenterCrop(size) if center_crop else transforms.RandomCrop(size),
                 transforms.ToTensor(),
                 transforms.Normalize([0.5], [0.5]),

examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py

@@ -799,6 +799,15 @@ def parse_args(input_args=None):
         default=False,
         help="Cache the VAE latents",
     )
+    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)
@@ -1069,7 +1078,10 @@ def __init__(
         self.original_sizes = []
         self.crop_top_lefts = []
         self.pixel_values = []
-        train_resize = transforms.Resize(size, interpolation=transforms.InterpolationMode.BILINEAR)
+        interpolation = getattr(transforms.InterpolationMode, args.image_interpolation_mode.upper(), None)
+        if interpolation is None:
+            raise ValueError(f"Unsupported interpolation mode {interpolation=}.")
+        train_resize = transforms.Resize(size, interpolation=interpolation)
         train_crop = transforms.CenterCrop(size) if center_crop else transforms.RandomCrop(size)
         train_flip = transforms.RandomHorizontalFlip(p=1.0)
         train_transforms = transforms.Compose(
@@ -1146,7 +1158,7 @@ def __init__(
 
         self.image_transforms = transforms.Compose(
             [
-                transforms.Resize(size, interpolation=transforms.InterpolationMode.BILINEAR),
+                transforms.Resize(size, interpolation=interpolation),
                 transforms.CenterCrop(size) if center_crop else transforms.RandomCrop(size),
                 transforms.ToTensor(),
                 transforms.Normalize([0.5], [0.5]),