MCPcopy Create free account
hub / github.com/Francis-Rings/StableAnimator / parse_args

Function parse_args

train_single.py:387–829  ·  view source on GitHub ↗
()

Source from the content-addressed store, hash-verified

385
386
387def parse_args():
388 parser = argparse.ArgumentParser(
389 description="Script to train Stable Diffusion XL for InstructPix2Pix."
390 )
391 parser.add_argument(
392 "--pretrained_model_name_or_path",
393 type=str,
394 default=None,
395 required=True,
396 help="Path to pretrained model or model identifier from huggingface.co/models.",
397 )
398 parser.add_argument(
399 "--revision",
400 type=str,
401 default=None,
402 required=False,
403 help="Revision of pretrained model identifier from huggingface.co/models.",
404 )
405
406 parser.add_argument(
407 "--num_frames",
408 type=int,
409 default=14,
410 )
411 parser.add_argument(
412 "--dataset_type",
413 type=str,
414 default='ubc',
415 )
416 parser.add_argument(
417 "--num_validation_images",
418 type=int,
419 default=1,
420 help="Number of images that should be generated during validation with `validation_prompt`.",
421 )
422 parser.add_argument(
423 "--validation_steps",
424 type=int,
425 default=500,
426 help=(
427 "Run fine-tuning validation every X epochs. The validation process consists of running the text/image prompt"
428 " multiple times: `args.num_validation_images`."
429 ),
430 )
431 parser.add_argument(
432 "--output_dir",
433 type=str,
434 default="./outputs",
435 help="The output directory where the model predictions and checkpoints will be written.",
436 )
437 parser.add_argument(
438 "--seed", type=int, default=None, help="A seed for reproducible training."
439 )
440 parser.add_argument(
441 "--per_gpu_batch_size",
442 type=int,
443 default=1,
444 help="Batch size (per device) for the training dataloader.",

Callers 1

mainFunction · 0.70

Calls 1

getMethod · 0.80

Tested by

no test coverage detected