add VideoDatasetWithResizeAndRectangleCrop dataset resize crop (#13)

* fix issue 12:  train dataset _preprocess_data crop video

* add_argument  video_reshape_mode input videos are reshaped to this mode

* arg enable_model_cpu_offloading

* Add imageio-ffmpeg and imageio to requirements.txt

* apply changes to i2v lora script

* make style

---------

Co-authored-by: --unset <--unset>
Co-authored-by: Aryan <aryan@huggingface.co>

training/args.py

@@ -192,6 +192,12 @@ def _get_training_args(parser: argparse.ArgumentParser) -> None:
         default=720,
         help="All input videos are resized to this width.",
     )
+    parser.add_argument(
+        "--video_reshape_mode",
+        type=str,
+        default=None,
+        help="All input videos are reshaped to this mode. Choose between ['center', 'random', 'none']",
+    )
     parser.add_argument("--fps", type=int, default=8, help="All input videos will be used at this FPS.")
     parser.add_argument(
         "--max_num_frames",