Function train

sd3_train.py:65–991

(args)

def train(args):
    args_util.verify_training_args(args)
    accelerator_setup.prepare_dataset_args(args, True)
    # sdxl_train_util.verify_sdxl_training_args(args)
    deepspeed_utils.prepare_deepspeed_args(args)
    setup_logging(args, reset=True)

    # temporary: backward compatibility for deprecated options. remove in the future
    if not args.skip_cache_check:
        args.skip_cache_check = args.skip_latents_validity_check

    # assert (
    #     not args.weighted_captions
    # ), "weighted_captions is not supported currently / weighted_captionsは現在サポートされていません"
    # assert (
    #     not args.train_text_encoder or not args.cache_text_encoder_outputs
    # ), "cache_text_encoder_outputs is not supported when training text encoder / text encoderを学習するときはcache_text_encoder_outputsはサポートされていません"
    if args.cache_text_encoder_outputs_to_disk and not args.cache_text_encoder_outputs:
        logger.warning(
            "cache_text_encoder_outputs_to_disk is enabled, so cache_text_encoder_outputs is also enabled / cache_text_encoder_outputs_to_diskが有効になっているため、cache_text_encoder_outputsも有効になります"
        )
        args.cache_text_encoder_outputs = True

    assert not args.train_text_encoder or (args.use_t5xxl_cache_only or not args.cache_text_encoder_outputs), (
        "when training text encoder, text encoder outputs must not be cached (except for T5XXL)"
        + " / text encoderの学習時はtext encoderの出力はキャッシュできません（t5xxlのみキャッシュすることは可能です）"
    )

    if args.use_t5xxl_cache_only and not args.cache_text_encoder_outputs:
        logger.warning(
            "use_t5xxl_cache_only is enabled, so cache_text_encoder_outputs is automatically enabled."
            + " / use_t5xxl_cache_onlyが有効なため、cache_text_encoder_outputsも自動的に有効になります"
        )
        args.cache_text_encoder_outputs = True

    if args.train_t5xxl:
        assert (
            args.train_text_encoder
        ), "when training T5XXL, text encoder (CLIP-L/G) must be trained / T5XXLを学習するときはtext encoder (CLIP-L/G)も学習する必要があります"
        assert (
            not args.cache_text_encoder_outputs
        ), "when training T5XXL, t5xxl output must not be cached / T5XXLを学習するときはt5xxlの出力をキャッシュできません"

    cache_latents = args.cache_latents
    use_dreambooth_method = args.in_json is None

    if args.seed is not None:
        set_seed(args.seed)  # 乱数系列を初期化する

    # prepare caching strategy: this must be set before preparing dataset. because dataset may use this strategy for initialization.
    if args.cache_latents:
        latents_caching_strategy = strategy_sd3.Sd3LatentsCachingStrategy(
            args.cache_latents_to_disk, args.vae_batch_size, args.skip_cache_check
        )
        strategy_base.LatentsCachingStrategy.set_strategy(latents_caching_strategy)

    # データセットを準備する
    if args.dataset_class is None: