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

Function parse_args

train.py:383–818  ·  view source on GitHub ↗
()

Source from the content-addressed store, hash-verified

381
382
383def parse_args():
384 parser = argparse.ArgumentParser(
385 description="Script to train Stable Diffusion XL for InstructPix2Pix."
386 )
387 parser.add_argument(
388 "--pretrained_model_name_or_path",
389 type=str,
390 default=None,
391 required=True,
392 help="Path to pretrained model or model identifier from huggingface.co/models.",
393 )
394 parser.add_argument(
395 "--revision",
396 type=str,
397 default=None,
398 required=False,
399 help="Revision of pretrained model identifier from huggingface.co/models.",
400 )
401
402 parser.add_argument(
403 "--num_frames",
404 type=int,
405 default=14,
406 )
407 parser.add_argument(
408 "--dataset_type",
409 type=str,
410 default='ubc',
411 )
412 parser.add_argument(
413 "--num_validation_images",
414 type=int,
415 default=1,
416 help="Number of images that should be generated during validation with `validation_prompt`.",
417 )
418 parser.add_argument(
419 "--validation_steps",
420 type=int,
421 default=500,
422 help=(
423 "Run fine-tuning validation every X epochs. The validation process consists of running the text/image prompt"
424 " multiple times: `args.num_validation_images`."
425 ),
426 )
427 parser.add_argument(
428 "--output_dir",
429 type=str,
430 default="./outputs",
431 help="The output directory where the model predictions and checkpoints will be written.",
432 )
433 parser.add_argument(
434 "--seed", type=int, default=None, help="A seed for reproducible training."
435 )
436 parser.add_argument(
437 "--per_gpu_batch_size",
438 type=int,
439 default=1,
440 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