Merge branch 'main' into quantized-hidream-training

Author: sayakpaul

examples/dreambooth/train_dreambooth_lora_sdxl.py

@@ -852,7 +852,7 @@ 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/text_to_image/train_text_to_image_sdxl.py

@@ -470,6 +470,15 @@ def parse_args(input_args=None):
         "--enable_xformers_memory_efficient_attention", action="store_true", help="Whether or not to use xformers."
     )
     parser.add_argument("--noise_offset", type=float, default=0, help="The scale of noise offset.")
+    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)
@@ -861,7 +870,10 @@ def load_model_hook(models, input_dir):
             )
 
     # Preprocessing the datasets.
-    train_resize = transforms.Resize(args.resolution, 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(args.resolution, interpolation=interpolation)
     train_crop = transforms.CenterCrop(args.resolution) if args.center_crop else transforms.RandomCrop(args.resolution)
     train_flip = transforms.RandomHorizontalFlip(p=1.0)
     train_transforms = transforms.Compose([transforms.ToTensor(), transforms.Normalize([0.5], [0.5])])