Upload 4 files

sdxl_train.py

@@ -0,0 +1,819 @@
+# training with captions
+
+import argparse
+import gc
+import math
+import os
+from multiprocessing import Value
+from typing import List
+import toml
+
+from tqdm import tqdm
+import torch
+
+from library.ipex_interop import init_ipex
+
+init_ipex()
+
+from accelerate.utils import set_seed
+from diffusers import DDPMScheduler
+from library import sdxl_model_util
+
+import library.train_util as train_util
+import library.config_util as config_util
+import library.sdxl_train_util as sdxl_train_util
+from library.config_util import (
+    ConfigSanitizer,
+    BlueprintGenerator,
+)
+import library.custom_train_functions as custom_train_functions
+from library.custom_train_functions import (
+    apply_snr_weight,
+    prepare_scheduler_for_custom_training,
+    scale_v_prediction_loss_like_noise_prediction,
+    add_v_prediction_like_loss,
+    apply_debiased_estimation,
+)
+from library.sdxl_original_unet import SdxlUNet2DConditionModel
+from library.train_util import EMAModel
+
+
+UNET_NUM_BLOCKS_FOR_BLOCK_LR = 23
+
+
+def get_block_params_to_optimize(unet: SdxlUNet2DConditionModel, block_lrs: List[float]) -> List[dict]:
+    block_params = [[] for _ in range(len(block_lrs))]
+
+    for i, (name, param) in enumerate(unet.named_parameters()):
+        if name.startswith("time_embed.") or name.startswith("label_emb."):
+            block_index = 0  # 0
+        elif name.startswith("input_blocks."):  # 1-9
+            block_index = 1 + int(name.split(".")[1])
+        elif name.startswith("middle_block."):  # 10-12
+            block_index = 10 + int(name.split(".")[1])
+        elif name.startswith("output_blocks."):  # 13-21
+            block_index = 13 + int(name.split(".")[1])
+        elif name.startswith("out."):  # 22
+            block_index = 22
+        else:
+            raise ValueError(f"unexpected parameter name: {name}")
+
+        block_params[block_index].append(param)
+
+    params_to_optimize = []
+    for i, params in enumerate(block_params):
+        if block_lrs[i] == 0:  # 0のときは学習しない do not optimize when lr is 0
+            continue
+        params_to_optimize.append({"params": params, "lr": block_lrs[i]})
+
+    return params_to_optimize
+
+
+def append_block_lr_to_logs(block_lrs, logs, lr_scheduler, optimizer_type):
+    names = []
+    block_index = 0
+    while block_index < UNET_NUM_BLOCKS_FOR_BLOCK_LR + 2:
+        if block_index < UNET_NUM_BLOCKS_FOR_BLOCK_LR:
+            if block_lrs[block_index] == 0:
+                block_index += 1
+                continue
+            names.append(f"block{block_index}")
+        elif block_index == UNET_NUM_BLOCKS_FOR_BLOCK_LR:
+            names.append("text_encoder1")
+        elif block_index == UNET_NUM_BLOCKS_FOR_BLOCK_LR + 1:
+            names.append("text_encoder2")
+
+        block_index += 1
+
+    train_util.append_lr_to_logs_with_names(logs, lr_scheduler, optimizer_type, names)
+
+
+def train(args):
+    train_util.verify_training_args(args)
+    train_util.prepare_dataset_args(args, True)
+    sdxl_train_util.verify_sdxl_training_args(args)
+
+    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.block_lr:
+        block_lrs = [float(lr) for lr in args.block_lr.split(",")]
+        assert (
+            len(block_lrs) == UNET_NUM_BLOCKS_FOR_BLOCK_LR
+        ), f"block_lr must have {UNET_NUM_BLOCKS_FOR_BLOCK_LR} values / block_lrは{UNET_NUM_BLOCKS_FOR_BLOCK_LR}個の値を指定してください"
+    else:
+        block_lrs = None
+
+    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
+
+    tokenizer1, tokenizer2 = sdxl_train_util.load_tokenizers(args)
+
+    # データセットを準備する
+    if args.dataset_class is None:
+        blueprint_generator = BlueprintGenerator(ConfigSanitizer(True, True, False, True))
+        if args.dataset_config is not None:
+            print(f"Load dataset config from {args.dataset_config}")
+            user_config = config_util.load_user_config(args.dataset_config)
+            ignored = ["train_data_dir", "in_json"]
+            if any(getattr(args, attr) is not None for attr in ignored):
+                print(
+                    "ignore following options because config file is found: {0} / 設定ファイルが利用されるため以下のオプションは無視されます: {0}".format(
+                        ", ".join(ignored)
+                    )
+                )
+        else:
+            if use_dreambooth_method:
+                print("Using DreamBooth method.")
+                user_config = {
+                    "datasets": [
+                        {
+                            "subsets": config_util.generate_dreambooth_subsets_config_by_subdirs(
+                                args.train_data_dir, args.reg_data_dir
+                            )
+                        }
+                    ]
+                }
+            else:
+                print("Training with captions.")
+                user_config = {
+                    "datasets": [
+                        {
+                            "subsets": [
+                                {
+                                    "image_dir": args.train_data_dir,
+                                    "metadata_file": args.in_json,
+                                }
+                            ]
+                        }
+                    ]
+                }
+
+        blueprint = blueprint_generator.generate(user_config, args, tokenizer=[tokenizer1, tokenizer2])
+        train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
+    else:
+        train_dataset_group = train_util.load_arbitrary_dataset(args, [tokenizer1, tokenizer2])
+
+    current_epoch = Value("i", 0)
+    current_step = Value("i", 0)
+    ds_for_collator = train_dataset_group if args.max_data_loader_n_workers == 0 else None
+    collator = train_util.collator_class(current_epoch, current_step, ds_for_collator)
+
+    train_dataset_group.verify_bucket_reso_steps(32)
+
+    if args.debug_dataset:
+        train_util.debug_dataset(train_dataset_group, True)
+        return
+    if len(train_dataset_group) == 0:
+        print(
+            "No data found. Please verify the metadata file and train_data_dir option. / 画像がありません。メタデータおよびtrain_data_dirオプションを確認してください。"
+        )
+        return
+
+    if cache_latents:
+        assert (
+            train_dataset_group.is_latent_cacheable()
+        ), "when caching latents, either color_aug or random_crop cannot be used / latentをキャッシュするときはcolor_augとrandom_cropは使えません"
+
+    if args.cache_text_encoder_outputs:
+        assert (
+            train_dataset_group.is_text_encoder_output_cacheable()
+        ), "when caching text encoder output, either caption_dropout_rate, shuffle_caption, token_warmup_step or caption_tag_dropout_rate cannot be used / text encoderの出力をキャッシュするときはcaption_dropout_rate, shuffle_caption, token_warmup_step, caption_tag_dropout_rateは使えません"
+
+    # acceleratorを準備する
+    print("prepare accelerator")
+    accelerator = train_util.prepare_accelerator(args)
+
+    # mixed precisionに対応した型を用意しておき適宜castする
+    weight_dtype, save_dtype = train_util.prepare_dtype(args)
+    vae_dtype = torch.float32 if args.no_half_vae else weight_dtype
+
+    # モデルを読み込む
+    (
+        load_stable_diffusion_format,
+        text_encoder1,
+        text_encoder2,
+        vae,
+        unet,
+        logit_scale,
+        ckpt_info,
+    ) = sdxl_train_util.load_target_model(args, accelerator, "sdxl", weight_dtype)
+    # logit_scale = logit_scale.to(accelerator.device, dtype=weight_dtype)
+
+    # verify load/save model formats
+    if load_stable_diffusion_format:
+        src_stable_diffusion_ckpt = args.pretrained_model_name_or_path
+        src_diffusers_model_path = None
+    else:
+        src_stable_diffusion_ckpt = None
+        src_diffusers_model_path = args.pretrained_model_name_or_path
+
+    if args.save_model_as is None:
+        save_stable_diffusion_format = load_stable_diffusion_format
+        use_safetensors = args.use_safetensors
+    else:
+        save_stable_diffusion_format = args.save_model_as.lower() == "ckpt" or args.save_model_as.lower() == "safetensors"
+        use_safetensors = args.use_safetensors or ("safetensors" in args.save_model_as.lower())
+        # assert save_stable_diffusion_format, "save_model_as must be ckpt or safetensors / save_model_asはckptかsafetensorsである必要があります"
+
+    # Diffusers版のxformers使用フラグを設定する関数
+    def set_diffusers_xformers_flag(model, valid):
+        def fn_recursive_set_mem_eff(module: torch.nn.Module):
+            if hasattr(module, "set_use_memory_efficient_attention_xformers"):
+                module.set_use_memory_efficient_attention_xformers(valid)
+
+            for child in module.children():
+                fn_recursive_set_mem_eff(child)
+
+        fn_recursive_set_mem_eff(model)
+
+    # モデルに xformers とか memory efficient attention を組み込む
+    if args.diffusers_xformers:
+        # もうU-Netを独自にしたので動かないけどVAEのxformersは動くはず
+        accelerator.print("Use xformers by Diffusers")
+        # set_diffusers_xformers_flag(unet, True)
+        set_diffusers_xformers_flag(vae, True)
+    else:
+        # Windows版のxformersはfloatで学習できなかったりするのでxformersを使わない設定も可能にしておく必要がある
+        accelerator.print("Disable Diffusers' xformers")
+        train_util.replace_unet_modules(unet, args.mem_eff_attn, args.xformers, args.sdpa)
+        if torch.__version__ >= "2.0.0":  # PyTorch 2.0.0 以上対応のxformersなら以下が使える
+            vae.set_use_memory_efficient_attention_xformers(args.xformers)
+
+    # 学習を準備する
+    if cache_latents:
+        vae.to(accelerator.device, dtype=vae_dtype)
+        vae.requires_grad_(False)
+        vae.eval()
+        with torch.no_grad():
+            train_dataset_group.cache_latents(vae, args.vae_batch_size, args.cache_latents_to_disk, accelerator.is_main_process)
+        vae.to("cpu")
+        if torch.cuda.is_available():
+            torch.cuda.empty_cache()
+        gc.collect()
+
+        accelerator.wait_for_everyone()
+
+    # 学習を準備する：モデルを適切な状態にする
+    if args.gradient_checkpointing:
+        unet.enable_gradient_checkpointing()
+    train_unet = args.learning_rate > 0
+    train_text_encoder1 = False
+    train_text_encoder2 = False
+
+    if args.train_text_encoder:
+        # TODO each option for two text encoders?
+        accelerator.print("enable text encoder training")
+        if args.gradient_checkpointing:
+            text_encoder1.gradient_checkpointing_enable()
+            text_encoder2.gradient_checkpointing_enable()
+        lr_te1 = args.learning_rate_te1 if args.learning_rate_te1 is not None else args.learning_rate  # 0 means not train
+        lr_te2 = args.learning_rate_te2 if args.learning_rate_te2 is not None else args.learning_rate  # 0 means not train
+        train_text_encoder1 = lr_te1 > 0
+        train_text_encoder2 = lr_te2 > 0
+
+        # caching one text encoder output is not supported
+        if not train_text_encoder1:
+            text_encoder1.to(weight_dtype)
+        if not train_text_encoder2:
+            text_encoder2.to(weight_dtype)
+        text_encoder1.requires_grad_(train_text_encoder1)
+        text_encoder2.requires_grad_(train_text_encoder2)
+        text_encoder1.train(train_text_encoder1)
+        text_encoder2.train(train_text_encoder2)
+    else:
+        text_encoder1.to(weight_dtype)
+        text_encoder2.to(weight_dtype)
+        text_encoder1.requires_grad_(False)
+        text_encoder2.requires_grad_(False)
+        text_encoder1.eval()
+        text_encoder2.eval()
+
+        # TextEncoderの出力をキャッシュする
+        if args.cache_text_encoder_outputs:
+            # Text Encodes are eval and no grad
+            with torch.no_grad(), accelerator.autocast():
+                train_dataset_group.cache_text_encoder_outputs(
+                    (tokenizer1, tokenizer2),
+                    (text_encoder1, text_encoder2),
+                    accelerator.device,
+                    None,
+                    args.cache_text_encoder_outputs_to_disk,
+                    accelerator.is_main_process,
+                )
+            accelerator.wait_for_everyone()
+
+    if not cache_latents:
+        vae.requires_grad_(False)
+        vae.eval()
+        vae.to(accelerator.device, dtype=vae_dtype)
+
+    unet.requires_grad_(train_unet)
+    if not train_unet:
+        unet.to(accelerator.device, dtype=weight_dtype)  # because of unet is not prepared
+
+    training_models = []
+    params_to_optimize = []
+    if train_unet:
+        training_models.append(unet)
+        if block_lrs is None:
+            params_to_optimize.append({"params": list(unet.parameters()), "lr": args.learning_rate})
+        else:
+            params_to_optimize.extend(get_block_params_to_optimize(unet, block_lrs))
+
+    if train_text_encoder1:
+        training_models.append(text_encoder1)
+        params_to_optimize.append({"params": list(text_encoder1.parameters()), "lr": args.learning_rate_te1 or args.learning_rate})
+    if train_text_encoder2:
+        training_models.append(text_encoder2)
+        params_to_optimize.append({"params": list(text_encoder2.parameters()), "lr": args.learning_rate_te2 or args.learning_rate})
+
+    # calculate number of trainable parameters
+    n_params = 0
+    for params in params_to_optimize:
+        for p in params["params"]:
+            n_params += p.numel()
+
+    accelerator.print(f"train unet: {train_unet}, text_encoder1: {train_text_encoder1}, text_encoder2: {train_text_encoder2}")
+    accelerator.print(f"number of models: {len(training_models)}")
+    accelerator.print(f"number of trainable parameters: {n_params}")
+
+    # 学習に必要なクラスを準備する
+    accelerator.print("prepare optimizer, data loader etc.")
+    _, _, optimizer = train_util.get_optimizer(args, trainable_params=params_to_optimize)
+
+    # dataloaderを準備する
+    # DataLoaderのプロセス数：0はメインプロセスになる
+    n_workers = min(args.max_data_loader_n_workers, os.cpu_count() - 1)  # cpu_count-1 ただし最大で指定された数まで
+    train_dataloader = torch.utils.data.DataLoader(
+        train_dataset_group,
+        batch_size=1,
+        shuffle=True,
+        collate_fn=collator,
+        num_workers=n_workers,
+        persistent_workers=args.persistent_data_loader_workers,
+    )
+
+    # 学習ステップ数を計算する
+    if args.max_train_epochs is not None:
+        args.max_train_steps = args.max_train_epochs * math.ceil(
+            len(train_dataloader) / accelerator.num_processes / args.gradient_accumulation_steps
+        )
+        accelerator.print(f"override steps. steps for {args.max_train_epochs} epochs is / 指定エポックまでのステップ数: {args.max_train_steps}")
+
+    # データセット側にも学習ステップを送信
+    train_dataset_group.set_max_train_steps(args.max_train_steps)
+
+    # lr schedulerを用意する
+    lr_scheduler = train_util.get_scheduler_fix(args, optimizer, accelerator.num_processes)
+
+    # 実験的機能：勾配も含めたfp16/bf16学習を行う　モデル全体をfp16/bf16にする
+    if args.full_fp16:
+        assert (
+            args.mixed_precision == "fp16"
+        ), "full_fp16 requires mixed precision='fp16' / full_fp16を使う場合はmixed_precision='fp16'を指定してください。"
+        accelerator.print("enable full fp16 training.")
+        unet.to(weight_dtype)
+        text_encoder1.to(weight_dtype)
+        text_encoder2.to(weight_dtype)
+    elif args.full_bf16:
+        assert (
+            args.mixed_precision == "bf16"
+        ), "full_bf16 requires mixed precision='bf16' / full_bf16を使う場合はmixed_precision='bf16'を指定してください。"
+        accelerator.print("enable full bf16 training.")
+        unet.to(weight_dtype)
+        text_encoder1.to(weight_dtype)
+        text_encoder2.to(weight_dtype)
+
+    if args.enable_ema:
+        #ema_dtype = weight_dtype if (args.full_bf16 or args.full_fp16) else torch.float
+        ema = EMAModel(params_to_optimize, decay=args.ema_decay, beta=args.ema_exp_beta, max_train_steps=args.max_train_steps)
+        ema.to(accelerator.device, dtype=weight_dtype)
+        ema = accelerator.prepare(ema)
+    else: 
+        ema = None
+    # acceleratorがなんかよろしくやってくれるらしい
+    if train_unet:
+        unet = accelerator.prepare(unet)
+    if train_text_encoder1:
+        # freeze last layer and final_layer_norm in te1 since we use the output of the penultimate layer
+        text_encoder1.text_model.encoder.layers[-1].requires_grad_(False)
+        text_encoder1.text_model.final_layer_norm.requires_grad_(False)
+        text_encoder1 = accelerator.prepare(text_encoder1)
+    if train_text_encoder2:
+        text_encoder2 = accelerator.prepare(text_encoder2)
+
+    optimizer, train_dataloader, lr_scheduler = accelerator.prepare(optimizer, train_dataloader, lr_scheduler)
+
+    # TextEncoderの出力をキャッシュするときにはCPUへ移動する
+    if args.cache_text_encoder_outputs:
+        # move Text Encoders for sampling images. Text Encoder doesn't work on CPU with fp16
+        text_encoder1.to("cpu", dtype=torch.float32)
+        text_encoder2.to("cpu", dtype=torch.float32)
+        if torch.cuda.is_available():
+            torch.cuda.empty_cache()
+    else:
+        # make sure Text Encoders are on GPU
+        text_encoder1.to(accelerator.device)
+        text_encoder2.to(accelerator.device)
+
+    # 実験的機能：勾配も含めたfp16学習を行う　PyTorchにパッチを当ててfp16でのgrad scaleを有効にする
+    if args.full_fp16:
+        train_util.patch_accelerator_for_fp16_training(accelerator)
+
+    # resumeする
+    train_util.resume_from_local_or_hf_if_specified(accelerator, args)
+
+    # epoch数を計算する
+    num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
+    num_train_epochs = math.ceil(args.max_train_steps / num_update_steps_per_epoch)
+    if (args.save_n_epoch_ratio is not None) and (args.save_n_epoch_ratio > 0):
+        args.save_every_n_epochs = math.floor(num_train_epochs / args.save_n_epoch_ratio) or 1
+
+    # 学習する
+    # total_batch_size = args.train_batch_size * accelerator.num_processes * args.gradient_accumulation_steps
+    accelerator.print("running training / 学習開始")
+    accelerator.print(f"  num examples / サンプル数: {train_dataset_group.num_train_images}")
+    accelerator.print(f"  num batches per epoch / 1epochのバッチ数: {len(train_dataloader)}")
+    accelerator.print(f"  num epochs / epoch数: {num_train_epochs}")
+    accelerator.print(f"  batch size per device / バッチサイズ: {', '.join([str(d.batch_size) for d in train_dataset_group.datasets])}")
+    # accelerator.print(
+    #     f"  total train batch size (with parallel & distributed & accumulation) / 総バッチサイズ（並列学習、勾配合計含む）: {total_batch_size}"
+    # )
+    accelerator.print(f"  gradient accumulation steps / 勾配を合計するステップ数 = {args.gradient_accumulation_steps}")
+    accelerator.print(f"  total optimization steps / 学習ステップ数: {args.max_train_steps}")
+
+    progress_bar = tqdm(range(args.max_train_steps), smoothing=0, disable=not accelerator.is_local_main_process, desc="steps")
+    global_step = 0
+
+    noise_scheduler = DDPMScheduler(
+        beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", num_train_timesteps=1000, clip_sample=False
+    )
+    prepare_scheduler_for_custom_training(noise_scheduler, accelerator.device)
+    if args.zero_terminal_snr:
+        custom_train_functions.fix_noise_scheduler_betas_for_zero_terminal_snr(noise_scheduler)
+
+    if accelerator.is_main_process:
+        init_kwargs = {}
+        if args.wandb_run_name:
+            init_kwargs['wandb'] = {'name': args.wandb_run_name}
+        if args.log_tracker_config is not None:
+            init_kwargs = toml.load(args.log_tracker_config)
+        accelerator.init_trackers("finetuning" if args.log_tracker_name is None else args.log_tracker_name, init_kwargs=init_kwargs)
+
+    # For --sample_at_first
+    sdxl_train_util.sample_images(
+        accelerator, args, 0, global_step, accelerator.device, vae, [tokenizer1, tokenizer2], [text_encoder1, text_encoder2], unet
+    )
+
+    loss_recorder = train_util.LossRecorder()
+    for epoch in range(num_train_epochs):
+        accelerator.print(f"\nepoch {epoch+1}/{num_train_epochs}")
+        current_epoch.value = epoch + 1
+
+        for m in training_models:
+            m.train()
+
+        for step, batch in enumerate(train_dataloader):
+            current_step.value = global_step
+            with accelerator.accumulate(*training_models):
+                if "latents" in batch and batch["latents"] is not None:
+                    latents = batch["latents"].to(accelerator.device).to(dtype=weight_dtype)
+                else:
+                    with torch.no_grad():
+                        # latentに変換
+                        latents = vae.encode(batch["images"].to(vae_dtype)).latent_dist.sample().to(weight_dtype)
+
+                        # NaNが含まれていれば警告を表示し0に置き換える
+                        if torch.any(torch.isnan(latents)):
+                            accelerator.print("NaN found in latents, replacing with zeros")
+                            latents = torch.nan_to_num(latents, 0, out=latents)
+                latents = latents * sdxl_model_util.VAE_SCALE_FACTOR
+
+                if "text_encoder_outputs1_list" not in batch or batch["text_encoder_outputs1_list"] is None:
+                    input_ids1 = batch["input_ids"]
+                    input_ids2 = batch["input_ids2"]
+                    with torch.set_grad_enabled(args.train_text_encoder):
+                        # Get the text embedding for conditioning
+                        # TODO support weighted captions
+                        # if args.weighted_captions:
+                        #     encoder_hidden_states = get_weighted_text_embeddings(
+                        #         tokenizer,
+                        #         text_encoder,
+                        #         batch["captions"],
+                        #         accelerator.device,
+                        #         args.max_token_length // 75 if args.max_token_length else 1,
+                        #         clip_skip=args.clip_skip,
+                        #     )
+                        # else:
+                        input_ids1 = input_ids1.to(accelerator.device)
+                        input_ids2 = input_ids2.to(accelerator.device)
+                        # unwrap_model is fine for models not wrapped by accelerator
+                        encoder_hidden_states1, encoder_hidden_states2, pool2 = train_util.get_hidden_states_sdxl(
+                            args.max_token_length,
+                            input_ids1,
+                            input_ids2,
+                            tokenizer1,
+                            tokenizer2,
+                            text_encoder1,
+                            text_encoder2,
+                            None if not args.full_fp16 else weight_dtype,
+                            accelerator=accelerator,
+                        )
+                else:
+                    encoder_hidden_states1 = batch["text_encoder_outputs1_list"].to(accelerator.device).to(weight_dtype)
+                    encoder_hidden_states2 = batch["text_encoder_outputs2_list"].to(accelerator.device).to(weight_dtype)
+                    pool2 = batch["text_encoder_pool2_list"].to(accelerator.device).to(weight_dtype)
+
+                    # # verify that the text encoder outputs are correct
+                    # ehs1, ehs2, p2 = train_util.get_hidden_states_sdxl(
+                    #     args.max_token_length,
+                    #     batch["input_ids"].to(text_encoder1.device),
+                    #     batch["input_ids2"].to(text_encoder1.device),
+                    #     tokenizer1,
+                    #     tokenizer2,
+                    #     text_encoder1,
+                    #     text_encoder2,
+                    #     None if not args.full_fp16 else weight_dtype,
+                    # )
+                    # b_size = encoder_hidden_states1.shape[0]
+                    # assert ((encoder_hidden_states1.to("cpu") - ehs1.to(dtype=weight_dtype)).abs().max() > 1e-2).sum() <= b_size * 2
+                    # assert ((encoder_hidden_states2.to("cpu") - ehs2.to(dtype=weight_dtype)).abs().max() > 1e-2).sum() <= b_size * 2
+                    # assert ((pool2.to("cpu") - p2.to(dtype=weight_dtype)).abs().max() > 1e-2).sum() <= b_size * 2
+                    # print("text encoder outputs verified")
+
+                # get size embeddings
+                orig_size = batch["original_sizes_hw"]
+                crop_size = batch["crop_top_lefts"]
+                target_size = batch["target_sizes_hw"]
+                embs = sdxl_train_util.get_size_embeddings(orig_size, crop_size, target_size, accelerator.device).to(weight_dtype)
+
+                # concat embeddings
+                vector_embedding = torch.cat([pool2, embs], dim=1).to(weight_dtype)
+                text_embedding = torch.cat([encoder_hidden_states1, encoder_hidden_states2], dim=2).to(weight_dtype)
+
+                # Sample noise, sample a random timestep for each image, and add noise to the latents,
+                # with noise offset and/or multires noise if specified
+                noise, noisy_latents, timesteps = train_util.get_noise_noisy_latents_and_timesteps(args, noise_scheduler, latents)
+
+                noisy_latents = noisy_latents.to(weight_dtype)  # TODO check why noisy_latents is not weight_dtype
+
+                # Predict the noise residual
+                with accelerator.autocast():
+                    noise_pred = unet(noisy_latents, timesteps, text_embedding, vector_embedding)
+
+                target = noise
+
+                if (
+                    args.min_snr_gamma
+                    or args.scale_v_pred_loss_like_noise_pred
+                    or args.v_pred_like_loss
+                    or args.debiased_estimation_loss
+                ):
+                    # do not mean over batch dimension for snr weight or scale v-pred loss
+                    loss = torch.nn.functional.mse_loss(noise_pred.float(), target.float(), reduction="none")
+                    loss = loss.mean([1, 2, 3])
+
+                    if args.min_snr_gamma:
+                        loss = apply_snr_weight(loss, timesteps, noise_scheduler, args.min_snr_gamma)
+                    if args.scale_v_pred_loss_like_noise_pred:
+                        loss = scale_v_prediction_loss_like_noise_prediction(loss, timesteps, noise_scheduler)
+                    if args.v_pred_like_loss:
+                        loss = add_v_prediction_like_loss(loss, timesteps, noise_scheduler, args.v_pred_like_loss)
+                    if args.debiased_estimation_loss:
+                        loss = apply_debiased_estimation(loss, timesteps, noise_scheduler)
+
+                    loss = loss.mean()  # mean over batch dimension
+                else:
+                    loss = torch.nn.functional.mse_loss(noise_pred.float(), target.float(), reduction="mean")
+
+                accelerator.backward(loss)
+                if accelerator.sync_gradients and args.max_grad_norm != 0.0:
+                    params_to_clip = []
+                    for m in training_models:
+                        params_to_clip.extend(m.parameters())
+                    accelerator.clip_grad_norm_(params_to_clip, args.max_grad_norm)
+
+                optimizer.step()
+                lr_scheduler.step()
+                optimizer.zero_grad(set_to_none=True)
+                if args.enable_ema:
+                    with torch.no_grad(), accelerator.autocast():
+                        ema.step(params_to_optimize)
+
+            # Checks if the accelerator has performed an optimization step behind the scenes
+            if accelerator.sync_gradients:
+                progress_bar.update(1)
+                global_step += 1
+
+                sdxl_train_util.sample_images(
+                    accelerator,
+                    args,
+                    None,
+                    global_step,
+                    accelerator.device,
+                    vae,
+                    [tokenizer1, tokenizer2],
+                    [text_encoder1, text_encoder2],
+                    unet,
+                )
+
+                # 指定ステップごとにモデルを保存
+                if args.save_every_n_steps is not None and global_step % args.save_every_n_steps == 0:
+                    accelerator.wait_for_everyone()
+                    if accelerator.is_main_process:
+                        src_path = src_stable_diffusion_ckpt if save_stable_diffusion_format else src_diffusers_model_path
+                        sdxl_train_util.save_sd_model_on_epoch_end_or_stepwise(
+                            args,
+                            False,
+                            accelerator,
+                            src_path,
+                            save_stable_diffusion_format,
+                            use_safetensors,
+                            save_dtype,
+                            epoch,
+                            num_train_epochs,
+                            global_step,
+                            accelerator.unwrap_model(text_encoder1),
+                            accelerator.unwrap_model(text_encoder2),
+                            accelerator.unwrap_model(unet),
+                            vae,
+                            logit_scale,
+                            ckpt_info,
+                            ema=ema,
+                            params_to_replace=params_to_optimize,
+                        )
+
+            current_loss = loss.detach().item()  # 平均なのでbatch sizeは関係ないはず
+            if args.logging_dir is not None:
+                logs = {"loss": current_loss}
+                if block_lrs is None:
+                    train_util.append_lr_to_logs(logs, lr_scheduler, args.optimizer_type, including_unet=train_unet)
+                else:
+                    append_block_lr_to_logs(block_lrs, logs, lr_scheduler, args.optimizer_type)  # U-Net is included in block_lrs
+
+                accelerator.log(logs, step=global_step)
+
+            loss_recorder.add(epoch=epoch, step=step, loss=current_loss)
+            avr_loss: float = loss_recorder.moving_average
+            logs = {"avr_loss": avr_loss}  # , "lr": lr_scheduler.get_last_lr()[0]}
+            progress_bar.set_postfix(**logs)
+
+            if global_step >= args.max_train_steps:
+                break
+
+        if args.logging_dir is not None:
+            logs = {"loss/epoch": loss_recorder.moving_average}
+            accelerator.log(logs, step=epoch + 1)
+
+        accelerator.wait_for_everyone()
+
+        if args.save_every_n_epochs is not None:
+            if accelerator.is_main_process:
+                src_path = src_stable_diffusion_ckpt if save_stable_diffusion_format else src_diffusers_model_path
+                sdxl_train_util.save_sd_model_on_epoch_end_or_stepwise(
+                    args,
+                    True,
+                    accelerator,
+                    src_path,
+                    save_stable_diffusion_format,
+                    use_safetensors,
+                    save_dtype,
+                    epoch,
+                    num_train_epochs,
+                    global_step,
+                    accelerator.unwrap_model(text_encoder1),
+                    accelerator.unwrap_model(text_encoder2),
+                    accelerator.unwrap_model(unet),
+                    vae,
+                    logit_scale,
+                    ckpt_info,
+                    ema=ema,
+                    params_to_replace=params_to_optimize,
+                )
+
+        sdxl_train_util.sample_images(
+            accelerator,
+            args,
+            epoch + 1,
+            global_step,
+            accelerator.device,
+            vae,
+            [tokenizer1, tokenizer2],
+            [text_encoder1, text_encoder2],
+            unet,
+        )
+
+    is_main_process = accelerator.is_main_process
+    # if is_main_process:
+    unet = accelerator.unwrap_model(unet)
+    text_encoder1 = accelerator.unwrap_model(text_encoder1)
+    text_encoder2 = accelerator.unwrap_model(text_encoder2)
+    if args.enable_ema:
+        ema = accelerator.unwrap_model(ema)
+
+    accelerator.end_training()
+
+    if args.save_state:  # and is_main_process:
+        train_util.save_state_on_train_end(args, accelerator)
+
+    del accelerator  # この後メモリを使うのでこれは消す
+
+    if is_main_process:
+        src_path = src_stable_diffusion_ckpt if save_stable_diffusion_format else src_diffusers_model_path
+        if args.enable_ema and not args.ema_save_only_ema_weights:
+            temp_name = args.output_name
+            args.output_name = args.output_name + "-non-EMA"
+            sdxl_train_util.save_sd_model_on_train_end(
+                args,
+                src_path,
+                save_stable_diffusion_format,
+                use_safetensors,
+                save_dtype,
+                epoch,
+                global_step,
+                text_encoder1,
+                text_encoder2,
+                unet,
+                vae,
+                logit_scale,
+                ckpt_info,
+            )
+            args.output_name = temp_name
+        if args.enable_ema:
+            print("Saving EMA:")
+            ema.copy_to(params_to_optimize)
+
+        sdxl_train_util.save_sd_model_on_train_end(
+            args,
+            src_path,
+            save_stable_diffusion_format,
+            use_safetensors,
+            save_dtype,
+            epoch,
+            global_step,
+            text_encoder1,
+            text_encoder2,
+            unet,
+            vae,
+            logit_scale,
+            ckpt_info,
+        )
+        print("model saved.")
+
+
+def setup_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser()
+
+    train_util.add_sd_models_arguments(parser)
+    train_util.add_dataset_arguments(parser, True, True, True)
+    train_util.add_training_arguments(parser, False)
+    train_util.add_sd_saving_arguments(parser)
+    train_util.add_optimizer_arguments(parser)
+    config_util.add_config_arguments(parser)
+    custom_train_functions.add_custom_train_arguments(parser)
+    sdxl_train_util.add_sdxl_training_arguments(parser)
+
+    parser.add_argument(
+        "--learning_rate_te1",
+        type=float,
+        default=None,
+        help="learning rate for text encoder 1 (ViT-L) / text encoder 1 (ViT-L)の学習率",
+    )
+    parser.add_argument(
+        "--learning_rate_te2",
+        type=float,
+        default=None,
+        help="learning rate for text encoder 2 (BiG-G) / text encoder 2 (BiG-G)の学習率",
+    )
+
+    parser.add_argument("--diffusers_xformers", action="store_true", help="use xformers by diffusers / Diffusersでxformersを使用する")
+    parser.add_argument("--train_text_encoder", action="store_true", help="train text encoder / text encoderも学習する")
+    parser.add_argument(
+        "--no_half_vae",
+        action="store_true",
+        help="do not use fp16/bf16 VAE in mixed precision (use float VAE) / mixed precisionでも fp16/bf16 VAEを使わずfloat VAEを使う",
+    )
+    parser.add_argument(
+        "--block_lr",
+        type=str,
+        default=None,
+        help=f"learning rates for each block of U-Net, comma-separated, {UNET_NUM_BLOCKS_FOR_BLOCK_LR} values / "
+        + f"U-Netの各ブロックの学習率、カンマ区切り、{UNET_NUM_BLOCKS_FOR_BLOCK_LR}個の値",
+    )
+
+    return parser
+
+
+if __name__ == "__main__":
+    parser = setup_parser()
+
+    args = parser.parse_args()
+    args = train_util.read_config_from_file(args, parser)
+
+    train(args)

sdxl_train_util.py

@@ -0,0 +1,389 @@
+import argparse
+import gc
+import math
+import os
+from typing import Optional
+import torch
+from accelerate import init_empty_weights
+from tqdm import tqdm
+from transformers import CLIPTokenizer
+from library import model_util, sdxl_model_util, train_util, sdxl_original_unet
+from library.sdxl_lpw_stable_diffusion import SdxlStableDiffusionLongPromptWeightingPipeline
+
+TOKENIZER1_PATH = "openai/clip-vit-large-patch14"
+TOKENIZER2_PATH = "laion/CLIP-ViT-bigG-14-laion2B-39B-b160k"
+
+# DEFAULT_NOISE_OFFSET = 0.0357
+
+
+def load_target_model(args, accelerator, model_version: str, weight_dtype):
+    # load models for each process
+    model_dtype = match_mixed_precision(args, weight_dtype)  # prepare fp16/bf16
+    for pi in range(accelerator.state.num_processes):
+        if pi == accelerator.state.local_process_index:
+            print(f"loading model for process {accelerator.state.local_process_index}/{accelerator.state.num_processes}")
+
+            (
+                load_stable_diffusion_format,
+                text_encoder1,
+                text_encoder2,
+                vae,
+                unet,
+                logit_scale,
+                ckpt_info,
+            ) = _load_target_model(
+                args.pretrained_model_name_or_path,
+                args.vae,
+                model_version,
+                weight_dtype,
+                accelerator.device if args.lowram else "cpu",
+                model_dtype,
+            )
+
+            # work on low-ram device
+            if args.lowram:
+                text_encoder1.to(accelerator.device)
+                text_encoder2.to(accelerator.device)
+                unet.to(accelerator.device)
+                vae.to(accelerator.device)
+
+            gc.collect()
+            torch.cuda.empty_cache()
+        accelerator.wait_for_everyone()
+
+    return load_stable_diffusion_format, text_encoder1, text_encoder2, vae, unet, logit_scale, ckpt_info
+
+
+def _load_target_model(
+    name_or_path: str, vae_path: Optional[str], model_version: str, weight_dtype, device="cpu", model_dtype=None
+):
+    # model_dtype only work with full fp16/bf16
+    name_or_path = os.readlink(name_or_path) if os.path.islink(name_or_path) else name_or_path
+    load_stable_diffusion_format = os.path.isfile(name_or_path)  # determine SD or Diffusers
+
+    if load_stable_diffusion_format:
+        print(f"load StableDiffusion checkpoint: {name_or_path}")
+        (
+            text_encoder1,
+            text_encoder2,
+            vae,
+            unet,
+            logit_scale,
+            ckpt_info,
+        ) = sdxl_model_util.load_models_from_sdxl_checkpoint(model_version, name_or_path, device, model_dtype)
+    else:
+        # Diffusers model is loaded to CPU
+        from diffusers import StableDiffusionXLPipeline
+
+        variant = "fp16" if weight_dtype == torch.float16 else None
+        print(f"load Diffusers pretrained models: {name_or_path}, variant={variant}")
+        try:
+            try:
+                pipe = StableDiffusionXLPipeline.from_pretrained(
+                    name_or_path, torch_dtype=model_dtype, variant=variant, tokenizer=None
+                )
+            except EnvironmentError as ex:
+                if variant is not None:
+                    print("try to load fp32 model")
+                    pipe = StableDiffusionXLPipeline.from_pretrained(name_or_path, variant=None, tokenizer=None)
+                else:
+                    raise ex
+        except EnvironmentError as ex:
+            print(
+                f"model is not found as a file or in Hugging Face, perhaps file name is wrong? / 指定したモデル名のファイル、またはHugging Faceのモデルが見つかりません。ファイル名が誤っているかもしれません: {name_or_path}"
+            )
+            raise ex
+
+        text_encoder1 = pipe.text_encoder
+        text_encoder2 = pipe.text_encoder_2
+
+        # convert to fp32 for cache text_encoders outputs
+        if text_encoder1.dtype != torch.float32:
+            text_encoder1 = text_encoder1.to(dtype=torch.float32)
+        if text_encoder2.dtype != torch.float32:
+            text_encoder2 = text_encoder2.to(dtype=torch.float32)
+
+        vae = pipe.vae
+        unet = pipe.unet
+        del pipe
+
+        # Diffusers U-Net to original U-Net
+        state_dict = sdxl_model_util.convert_diffusers_unet_state_dict_to_sdxl(unet.state_dict())
+        with init_empty_weights():
+            unet = sdxl_original_unet.SdxlUNet2DConditionModel()  # overwrite unet
+        sdxl_model_util._load_state_dict_on_device(unet, state_dict, device=device, dtype=model_dtype)
+        print("U-Net converted to original U-Net")
+
+        logit_scale = None
+        ckpt_info = None
+
+    # VAEを読み込む
+    if vae_path is not None:
+        vae = model_util.load_vae(vae_path, weight_dtype)
+        print("additional VAE loaded")
+
+    return load_stable_diffusion_format, text_encoder1, text_encoder2, vae, unet, logit_scale, ckpt_info
+
+
+def load_tokenizers(args: argparse.Namespace):
+    print("prepare tokenizers")
+
+    original_paths = [TOKENIZER1_PATH, TOKENIZER2_PATH]
+    tokeniers = []
+    for i, original_path in enumerate(original_paths):
+        tokenizer: CLIPTokenizer = None
+        if args.tokenizer_cache_dir:
+            local_tokenizer_path = os.path.join(args.tokenizer_cache_dir, original_path.replace("/", "_"))
+            if os.path.exists(local_tokenizer_path):
+                print(f"load tokenizer from cache: {local_tokenizer_path}")
+                tokenizer = CLIPTokenizer.from_pretrained(local_tokenizer_path)
+
+        if tokenizer is None:
+            tokenizer = CLIPTokenizer.from_pretrained(original_path)
+
+        if args.tokenizer_cache_dir and not os.path.exists(local_tokenizer_path):
+            print(f"save Tokenizer to cache: {local_tokenizer_path}")
+            tokenizer.save_pretrained(local_tokenizer_path)
+
+        if i == 1:
+            tokenizer.pad_token_id = 0  # fix pad token id to make same as open clip tokenizer
+
+        tokeniers.append(tokenizer)
+
+    if hasattr(args, "max_token_length") and args.max_token_length is not None:
+        print(f"update token length: {args.max_token_length}")
+
+    return tokeniers
+
+
+def match_mixed_precision(args, weight_dtype):
+    if args.full_fp16:
+        assert (
+            weight_dtype == torch.float16
+        ), "full_fp16 requires mixed precision='fp16' / full_fp16を使う場合はmixed_precision='fp16'を指定してください。"
+        return weight_dtype
+    elif args.full_bf16:
+        assert (
+            weight_dtype == torch.bfloat16
+        ), "full_bf16 requires mixed precision='bf16' / full_bf16を使う場合はmixed_precision='bf16'を指定してください。"
+        return weight_dtype
+    else:
+        return None
+
+
+def timestep_embedding(timesteps, dim, max_period=10000):
+    """
+    Create sinusoidal timestep embeddings.
+    :param timesteps: a 1-D Tensor of N indices, one per batch element.
+                      These may be fractional.
+    :param dim: the dimension of the output.
+    :param max_period: controls the minimum frequency of the embeddings.
+    :return: an [N x dim] Tensor of positional embeddings.
+    """
+    half = dim // 2
+    freqs = torch.exp(-math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32) / half).to(
+        device=timesteps.device
+    )
+    args = timesteps[:, None].float() * freqs[None]
+    embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
+    if dim % 2:
+        embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
+    return embedding
+
+
+def get_timestep_embedding(x, outdim):
+    assert len(x.shape) == 2
+    b, dims = x.shape[0], x.shape[1]
+    x = torch.flatten(x)
+    emb = timestep_embedding(x, outdim)
+    emb = torch.reshape(emb, (b, dims * outdim))
+    return emb
+
+
+def get_size_embeddings(orig_size, crop_size, target_size, device):
+    emb1 = get_timestep_embedding(orig_size, 256)
+    emb2 = get_timestep_embedding(crop_size, 256)
+    emb3 = get_timestep_embedding(target_size, 256)
+    vector = torch.cat([emb1, emb2, emb3], dim=1).to(device)
+    return vector
+
+
+def save_sd_model_on_train_end(
+    args: argparse.Namespace,
+    src_path: str,
+    save_stable_diffusion_format: bool,
+    use_safetensors: bool,
+    save_dtype: torch.dtype,
+    epoch: int,
+    global_step: int,
+    text_encoder1,
+    text_encoder2,
+    unet,
+    vae,
+    logit_scale,
+    ckpt_info,
+):
+    def sd_saver(ckpt_file, epoch_no, global_step):
+        sai_metadata = train_util.get_sai_model_spec(None, args, True, False, False, is_stable_diffusion_ckpt=True)
+        sdxl_model_util.save_stable_diffusion_checkpoint(
+            ckpt_file,
+            text_encoder1,
+            text_encoder2,
+            unet,
+            epoch_no,
+            global_step,
+            ckpt_info,
+            vae,
+            logit_scale,
+            sai_metadata,
+            save_dtype,
+        )
+
+    def diffusers_saver(out_dir):
+        sdxl_model_util.save_diffusers_checkpoint(
+            out_dir,
+            text_encoder1,
+            text_encoder2,
+            unet,
+            src_path,
+            vae,
+            use_safetensors=use_safetensors,
+            save_dtype=save_dtype,
+        )
+
+    train_util.save_sd_model_on_train_end_common(
+        args, save_stable_diffusion_format, use_safetensors, epoch, global_step, sd_saver, diffusers_saver
+    )
+
+
+# epochとstepの保存、メタデータにepoch/stepが含まれ引数が同じになるため、統合している
+# on_epoch_end: Trueならepoch終了時、Falseならstep経過時
+def save_sd_model_on_epoch_end_or_stepwise(
+    args: argparse.Namespace,
+    on_epoch_end: bool,
+    accelerator,
+    src_path,
+    save_stable_diffusion_format: bool,
+    use_safetensors: bool,
+    save_dtype: torch.dtype,
+    epoch: int,
+    num_train_epochs: int,
+    global_step: int,
+    text_encoder1,
+    text_encoder2,
+    unet,
+    vae,
+    logit_scale,
+    ckpt_info,
+    ema = None,
+    params_to_replace = None,
+):
+    def sd_saver(ckpt_file, epoch_no, global_step):
+        sai_metadata = train_util.get_sai_model_spec(None, args, True, False, False, is_stable_diffusion_ckpt=True)
+        sdxl_model_util.save_stable_diffusion_checkpoint(
+            ckpt_file,
+            text_encoder1,
+            text_encoder2,
+            unet,
+            epoch_no,
+            global_step,
+            ckpt_info,
+            vae,
+            logit_scale,
+            sai_metadata,
+            save_dtype,
+        )
+
+    def diffusers_saver(out_dir):
+        sdxl_model_util.save_diffusers_checkpoint(
+            out_dir,
+            text_encoder1,
+            text_encoder2,
+            unet,
+            src_path,
+            vae,
+            use_safetensors=use_safetensors,
+            save_dtype=save_dtype,
+        )
+
+    if args.enable_ema and not args.ema_save_only_ema_weights and ema:
+        temp_name = args.output_name
+        args.output_name = args.output_name + "-non-EMA"
+
+    train_util.save_sd_model_on_epoch_end_or_stepwise_common(
+        args,
+        on_epoch_end,
+        accelerator,
+        save_stable_diffusion_format,
+        use_safetensors,
+        epoch,
+        num_train_epochs,
+        global_step,
+        sd_saver,
+        diffusers_saver,
+    )
+    args.output_name = temp_name if temp_name else args.output_name
+    if args.enable_ema and ema:
+        with ema.ema_parameters(params_to_replace):
+            print("Saving EMA:")
+            train_util.save_sd_model_on_epoch_end_or_stepwise_common(
+                args,
+                on_epoch_end,
+                accelerator,
+                save_stable_diffusion_format,
+                use_safetensors,
+                epoch,
+                num_train_epochs,
+                global_step,
+                sd_saver,
+                diffusers_saver,
+            )
+
+
+def add_sdxl_training_arguments(parser: argparse.ArgumentParser):
+    parser.add_argument(
+        "--cache_text_encoder_outputs", action="store_true", help="cache text encoder outputs / text encoderの出力をキャッシュする"
+    )
+    parser.add_argument(
+        "--cache_text_encoder_outputs_to_disk",
+        action="store_true",
+        help="cache text encoder outputs to disk / text encoderの出力をディスクにキャッシュする",
+    )
+
+
+def verify_sdxl_training_args(args: argparse.Namespace, supportTextEncoderCaching: bool = True):
+    assert not args.v2, "v2 cannot be enabled in SDXL training / SDXL学習ではv2を有効にすることはできません"
+    if args.v_parameterization:
+        print("v_parameterization will be unexpected / SDXL学習ではv_parameterizationは想定外の動作になります")
+
+    if args.clip_skip is not None:
+        print("clip_skip will be unexpected / SDXL学習ではclip_skipは動作しません")
+
+    # if args.multires_noise_iterations:
+    #     print(
+    #         f"Warning: SDXL has been trained with noise_offset={DEFAULT_NOISE_OFFSET}, but noise_offset is disabled due to multires_noise_iterations / SDXLはnoise_offset={DEFAULT_NOISE_OFFSET}で学習されていますが、multires_noise_iterationsが有効になっているためnoise_offsetは無効になります"
+    #     )
+    # else:
+    #     if args.noise_offset is None:
+    #         args.noise_offset = DEFAULT_NOISE_OFFSET
+    #     elif args.noise_offset != DEFAULT_NOISE_OFFSET:
+    #         print(
+    #             f"Warning: SDXL has been trained with noise_offset={DEFAULT_NOISE_OFFSET} / SDXLはnoise_offset={DEFAULT_NOISE_OFFSET}で学習されています"
+    #         )
+    #     print(f"noise_offset is set to {args.noise_offset} / noise_offsetが{args.noise_offset}に設定されました")
+
+    assert (
+        not hasattr(args, "weighted_captions") or not args.weighted_captions
+    ), "weighted_captions cannot be enabled in SDXL training currently / SDXL学習では今のところweighted_captionsを有効にすることはできません"
+
+    if supportTextEncoderCaching:
+        if args.cache_text_encoder_outputs_to_disk and not args.cache_text_encoder_outputs:
+            args.cache_text_encoder_outputs = True
+            print(
+                "cache_text_encoder_outputs is enabled because cache_text_encoder_outputs_to_disk is enabled / "
+                + "cache_text_encoder_outputs_to_diskが有効になっているためcache_text_encoder_outputsが有効になりました"
+            )
+
+
+def sample_images(*args, **kwargs):
+    return train_util.sample_images_common(SdxlStableDiffusionLongPromptWeightingPipeline, *args, **kwargs)

train_db.py

@@ -0,0 +1,539 @@
+# DreamBooth training
+# XXX dropped option: fine_tune
+
+import gc
+import argparse
+import itertools
+import math
+import os
+from multiprocessing import Value
+import toml
+
+from tqdm import tqdm
+import torch
+
+from library.ipex_interop import init_ipex
+
+init_ipex()
+
+from accelerate.utils import set_seed
+from diffusers import DDPMScheduler
+
+import library.train_util as train_util
+import library.config_util as config_util
+from library.config_util import (
+    ConfigSanitizer,
+    BlueprintGenerator,
+)
+import library.custom_train_functions as custom_train_functions
+from library.custom_train_functions import (
+    apply_snr_weight,
+    get_weighted_text_embeddings,
+    prepare_scheduler_for_custom_training,
+    pyramid_noise_like,
+    apply_noise_offset,
+    scale_v_prediction_loss_like_noise_prediction,
+    apply_debiased_estimation,
+)
+
+# perlin_noise,
+
+
+def train(args):
+    train_util.verify_training_args(args)
+    train_util.prepare_dataset_args(args, False)
+
+    cache_latents = args.cache_latents
+
+    if args.seed is not None:
+        set_seed(args.seed)  # 乱数系列を初期化する
+
+    tokenizer = train_util.load_tokenizer(args)
+
+    # データセットを準備する
+    if args.dataset_class is None:
+        blueprint_generator = BlueprintGenerator(ConfigSanitizer(True, False, False, True))
+        if args.dataset_config is not None:
+            print(f"Load dataset config from {args.dataset_config}")
+            user_config = config_util.load_user_config(args.dataset_config)
+            ignored = ["train_data_dir", "reg_data_dir"]
+            if any(getattr(args, attr) is not None for attr in ignored):
+                print(
+                    "ignore following options because config file is found: {0} / 設定ファイルが利用されるため以下のオプションは無視されます: {0}".format(
+                        ", ".join(ignored)
+                    )
+                )
+        else:
+            user_config = {
+                "datasets": [
+                    {"subsets": config_util.generate_dreambooth_subsets_config_by_subdirs(args.train_data_dir, args.reg_data_dir)}
+                ]
+            }
+
+        blueprint = blueprint_generator.generate(user_config, args, tokenizer=tokenizer)
+        train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
+    else:
+        train_dataset_group = train_util.load_arbitrary_dataset(args, tokenizer)
+
+    current_epoch = Value("i", 0)
+    current_step = Value("i", 0)
+    ds_for_collator = train_dataset_group if args.max_data_loader_n_workers == 0 else None
+    collator = train_util.collator_class(current_epoch, current_step, ds_for_collator)
+
+    if args.no_token_padding:
+        train_dataset_group.disable_token_padding()
+
+    if args.debug_dataset:
+        train_util.debug_dataset(train_dataset_group)
+        return
+
+    if cache_latents:
+        assert (
+            train_dataset_group.is_latent_cacheable()
+        ), "when caching latents, either color_aug or random_crop cannot be used / latentをキャッシュするときはcolor_augとrandom_cropは使えません"
+
+    # acceleratorを準備する
+    print("prepare accelerator")
+
+    if args.gradient_accumulation_steps > 1:
+        print(
+            f"gradient_accumulation_steps is {args.gradient_accumulation_steps}. accelerate does not support gradient_accumulation_steps when training multiple models (U-Net and Text Encoder), so something might be wrong"
+        )
+        print(
+            f"gradient_accumulation_stepsが{args.gradient_accumulation_steps}に設定されています。accelerateは複数モデル（U-NetおよびText Encoder）の学習時にgradient_accumulation_stepsをサポートしていないため結果は未知数です"
+        )
+
+    accelerator = train_util.prepare_accelerator(args)
+
+    # mixed precisionに対応した型を用意しておき適宜castする
+    weight_dtype, save_dtype = train_util.prepare_dtype(args)
+    vae_dtype = torch.float32 if args.no_half_vae else weight_dtype
+
+    # モデルを読み込む
+    text_encoder, vae, unet, load_stable_diffusion_format = train_util.load_target_model(args, weight_dtype, accelerator)
+
+    # verify load/save model formats
+    if load_stable_diffusion_format:
+        src_stable_diffusion_ckpt = args.pretrained_model_name_or_path
+        src_diffusers_model_path = None
+    else:
+        src_stable_diffusion_ckpt = None
+        src_diffusers_model_path = args.pretrained_model_name_or_path
+
+    if args.save_model_as is None:
+        save_stable_diffusion_format = load_stable_diffusion_format
+        use_safetensors = args.use_safetensors
+    else:
+        save_stable_diffusion_format = args.save_model_as.lower() == "ckpt" or args.save_model_as.lower() == "safetensors"
+        use_safetensors = args.use_safetensors or ("safetensors" in args.save_model_as.lower())
+
+    # モデルに xformers とか memory efficient attention を組み込む
+    train_util.replace_unet_modules(unet, args.mem_eff_attn, args.xformers, args.sdpa)
+
+    # 学習を準備する
+    if cache_latents:
+        vae.to(accelerator.device, dtype=vae_dtype)
+        vae.requires_grad_(False)
+        vae.eval()
+        with torch.no_grad():
+            train_dataset_group.cache_latents(vae, args.vae_batch_size, args.cache_latents_to_disk, accelerator.is_main_process)
+        vae.to("cpu")
+        if torch.cuda.is_available():
+            torch.cuda.empty_cache()
+        gc.collect()
+
+        accelerator.wait_for_everyone()
+
+    # 学習を準備する：モデルを適切な状態にする
+    train_text_encoder = args.stop_text_encoder_training is None or args.stop_text_encoder_training >= 0
+    unet.requires_grad_(True)  # 念のため追加
+    text_encoder.requires_grad_(train_text_encoder)
+    if not train_text_encoder:
+        accelerator.print("Text Encoder is not trained.")
+
+    if args.gradient_checkpointing:
+        unet.enable_gradient_checkpointing()
+        text_encoder.gradient_checkpointing_enable()
+
+    if not cache_latents:
+        vae.requires_grad_(False)
+        vae.eval()
+        vae.to(accelerator.device, dtype=weight_dtype)
+
+    # 学習に必要なクラスを準備する
+    accelerator.print("prepare optimizer, data loader etc.")
+    if train_text_encoder:
+        if args.learning_rate_te is None:
+            # wightout list, adamw8bit is crashed
+            trainable_params = list(itertools.chain(unet.parameters(), text_encoder.parameters()))
+        else:
+            trainable_params = [
+                {"params": list(unet.parameters()), "lr": args.learning_rate},
+                {"params": list(text_encoder.parameters()), "lr": args.learning_rate_te},
+            ]
+    else:
+        trainable_params = unet.parameters()
+
+    _, _, optimizer = train_util.get_optimizer(args, trainable_params)
+
+    # dataloaderを準備する
+    # DataLoaderのプロセス数：0はメインプロセスになる
+    n_workers = min(args.max_data_loader_n_workers, os.cpu_count() - 1)  # cpu_count-1 ただし最大で指定された数まで
+    train_dataloader = torch.utils.data.DataLoader(
+        train_dataset_group,
+        batch_size=1,
+        shuffle=True,
+        collate_fn=collator,
+        num_workers=n_workers,
+        persistent_workers=args.persistent_data_loader_workers,
+    )
+
+    # 学習ステップ数を計算する
+    if args.max_train_epochs is not None:
+        args.max_train_steps = args.max_train_epochs * math.ceil(
+            len(train_dataloader) / accelerator.num_processes / args.gradient_accumulation_steps
+        )
+        accelerator.print(f"override steps. steps for {args.max_train_epochs} epochs is / 指定エポックまでのステップ数: {args.max_train_steps}")
+
+    # データセット側にも学習ステップを送信
+    train_dataset_group.set_max_train_steps(args.max_train_steps)
+
+    if args.stop_text_encoder_training is None:
+        args.stop_text_encoder_training = args.max_train_steps + 1  # do not stop until end
+
+    # lr schedulerを用意する TODO gradient_accumulation_stepsの扱いが何かおかしいかもしれない。後で確認する
+    lr_scheduler = train_util.get_scheduler_fix(args, optimizer, accelerator.num_processes)
+
+    # 実験的機能：勾配も含めたfp16学習を行う　モデル全体をfp16にする
+    if args.full_fp16:
+        assert (
+            args.mixed_precision == "fp16"
+        ), "full_fp16 requires mixed precision='fp16' / full_fp16を使う場合はmixed_precision='fp16'を指定してください。"
+        accelerator.print("enable full fp16 training.")
+        unet.to(weight_dtype)
+        text_encoder.to(weight_dtype)
+
+    if args.enable_ema:
+        #ema_dtype = weight_dtype if (args.full_bf16 or args.full_fp16) else torch.float
+        ema = EMAModel(params_to_optimize, decay=args.ema_decay, beta=args.ema_exp_beta, max_train_steps=args.max_train_steps)
+        ema.to(accelerator.device, dtype=weight_dtype)
+        ema = accelerator.prepare(ema)
+    else: 
+        ema = None
+    # acceleratorがなんかよろしくやってくれるらしい
+    if train_text_encoder:
+        unet, text_encoder, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
+            unet, text_encoder, optimizer, train_dataloader, lr_scheduler
+        )
+    else:
+        unet, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(unet, optimizer, train_dataloader, lr_scheduler)
+
+    if not train_text_encoder:
+        text_encoder.to(accelerator.device, dtype=weight_dtype)  # to avoid 'cpu' vs 'cuda' error
+
+    # 実験的機能：勾配も含めたfp16学習を行う　PyTorchにパッチを当ててfp16でのgrad scaleを有効にする
+    if args.full_fp16:
+        train_util.patch_accelerator_for_fp16_training(accelerator)
+
+    # resumeする
+    train_util.resume_from_local_or_hf_if_specified(accelerator, args)
+
+    # epoch数を計算する
+    num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
+    num_train_epochs = math.ceil(args.max_train_steps / num_update_steps_per_epoch)
+    if (args.save_n_epoch_ratio is not None) and (args.save_n_epoch_ratio > 0):
+        args.save_every_n_epochs = math.floor(num_train_epochs / args.save_n_epoch_ratio) or 1
+
+    # 学習する
+    total_batch_size = args.train_batch_size * accelerator.num_processes * args.gradient_accumulation_steps
+    accelerator.print("running training / 学習開始")
+    accelerator.print(f"  num train images * repeats / 学習画像の数×繰り返し回数: {train_dataset_group.num_train_images}")
+    accelerator.print(f"  num reg images / 正則化画像の数: {train_dataset_group.num_reg_images}")
+    accelerator.print(f"  num batches per epoch / 1epochのバッチ数: {len(train_dataloader)}")
+    accelerator.print(f"  num epochs / epoch数: {num_train_epochs}")
+    accelerator.print(f"  batch size per device / バッチサイズ: {args.train_batch_size}")
+    accelerator.print(
+        f"  total train batch size (with parallel & distributed & accumulation) / 総バッチサイズ（並列学習、勾配合計含む）: {total_batch_size}"
+    )
+    accelerator.print(f"  gradient ccumulation steps / 勾配を合計するステップ数 = {args.gradient_accumulation_steps}")
+    accelerator.print(f"  total optimization steps / 学習ステップ数: {args.max_train_steps}")
+
+    progress_bar = tqdm(range(args.max_train_steps), smoothing=0, disable=not accelerator.is_local_main_process, desc="steps")
+    global_step = 0
+
+    noise_scheduler = DDPMScheduler(
+        beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", num_train_timesteps=1000, clip_sample=False
+    )
+    prepare_scheduler_for_custom_training(noise_scheduler, accelerator.device)
+    if args.zero_terminal_snr:
+        custom_train_functions.fix_noise_scheduler_betas_for_zero_terminal_snr(noise_scheduler)
+
+    if accelerator.is_main_process:
+        init_kwargs = {}
+        if args.wandb_run_name:
+            init_kwargs['wandb'] = {'name': args.wandb_run_name}
+        if args.log_tracker_config is not None:
+            init_kwargs = toml.load(args.log_tracker_config)
+        accelerator.init_trackers("dreambooth" if args.log_tracker_name is None else args.log_tracker_name, init_kwargs=init_kwargs)
+
+    # For --sample_at_first
+    train_util.sample_images(accelerator, args, 0, global_step, accelerator.device, vae, tokenizer, text_encoder, unet)
+
+    loss_recorder = train_util.LossRecorder()
+    for epoch in range(num_train_epochs):
+        accelerator.print(f"\nepoch {epoch+1}/{num_train_epochs}")
+        current_epoch.value = epoch + 1
+
+        # 指定したステップ数までText Encoderを学習する：epoch最初の状態
+        unet.train()
+        # train==True is required to enable gradient_checkpointing
+        if args.gradient_checkpointing or global_step < args.stop_text_encoder_training:
+            text_encoder.train()
+
+        for step, batch in enumerate(train_dataloader):
+            current_step.value = global_step
+            # 指定したステップ数でText Encoderの学習を止める
+            if global_step == args.stop_text_encoder_training:
+                accelerator.print(f"stop text encoder training at step {global_step}")
+                if not args.gradient_checkpointing:
+                    text_encoder.train(False)
+                text_encoder.requires_grad_(False)
+
+            with accelerator.accumulate(unet):
+                with torch.no_grad():
+                    # latentに変換
+                    if cache_latents:
+                        latents = batch["latents"].to(accelerator.device)
+                    else:
+                        latents = vae.encode(batch["images"].to(dtype=weight_dtype)).latent_dist.sample()
+                    latents = latents * 0.18215
+                b_size = latents.shape[0]
+
+                # Get the text embedding for conditioning
+                with torch.set_grad_enabled(global_step < args.stop_text_encoder_training):
+                    if args.weighted_captions:
+                        encoder_hidden_states = get_weighted_text_embeddings(
+                            tokenizer,
+                            text_encoder,
+                            batch["captions"],
+                            accelerator.device,
+                            args.max_token_length // 75 if args.max_token_length else 1,
+                            clip_skip=args.clip_skip,
+                        )
+                    else:
+                        input_ids = batch["input_ids"].to(accelerator.device)
+                        encoder_hidden_states = train_util.get_hidden_states(
+                            args, input_ids, tokenizer, text_encoder, None if not args.full_fp16 else weight_dtype
+                        )
+
+                # Sample noise, sample a random timestep for each image, and add noise to the latents,
+                # with noise offset and/or multires noise if specified
+                noise, noisy_latents, timesteps = train_util.get_noise_noisy_latents_and_timesteps(args, noise_scheduler, latents)
+
+                # Predict the noise residual
+                with accelerator.autocast():
+                    noise_pred = unet(noisy_latents, timesteps, encoder_hidden_states).sample
+
+                if args.v_parameterization:
+                    # v-parameterization training
+                    target = noise_scheduler.get_velocity(latents, noise, timesteps)
+                else:
+                    target = noise
+
+                loss = torch.nn.functional.mse_loss(noise_pred.float(), target.float(), reduction="none")
+                loss = loss.mean([1, 2, 3])
+
+                loss_weights = batch["loss_weights"]  # 各sampleごとのweight
+                loss = loss * loss_weights
+
+                if args.min_snr_gamma:
+                    loss = apply_snr_weight(loss, timesteps, noise_scheduler, args.min_snr_gamma, args.v_parameterization)
+                if args.scale_v_pred_loss_like_noise_pred:
+                    loss = scale_v_prediction_loss_like_noise_prediction(loss, timesteps, noise_scheduler)
+                if args.debiased_estimation_loss:
+                    loss = apply_debiased_estimation(loss, timesteps, noise_scheduler)
+
+                loss = loss.mean()  # 平均なのでbatch_sizeで割る必要なし
+
+                accelerator.backward(loss)
+                if accelerator.sync_gradients and args.max_grad_norm != 0.0:
+                    if train_text_encoder:
+                        params_to_clip = itertools.chain(unet.parameters(), text_encoder.parameters())
+                    else:
+                        params_to_clip = unet.parameters()
+                    accelerator.clip_grad_norm_(params_to_clip, args.max_grad_norm)
+
+                optimizer.step()
+                lr_scheduler.step()
+                optimizer.zero_grad(set_to_none=True)
+                if args.enable_ema:
+                    with torch.no_grad(), accelerator.autocast():
+                        ema.step(params_to_optimize)
+
+            # Checks if the accelerator has performed an optimization step behind the scenes
+            if accelerator.sync_gradients:
+                progress_bar.update(1)
+                global_step += 1
+
+                train_util.sample_images(
+                    accelerator, args, None, global_step, accelerator.device, vae, tokenizer, text_encoder, unet
+                )
+
+                # 指定ステップごとにモデルを保存
+                if args.save_every_n_steps is not None and global_step % args.save_every_n_steps == 0:
+                    accelerator.wait_for_everyone()
+                    if accelerator.is_main_process:
+                        src_path = src_stable_diffusion_ckpt if save_stable_diffusion_format else src_diffusers_model_path
+                        train_util.save_sd_model_on_epoch_end_or_stepwise(
+                            args,
+                            False,
+                            accelerator,
+                            src_path,
+                            save_stable_diffusion_format,
+                            use_safetensors,
+                            save_dtype,
+                            epoch,
+                            num_train_epochs,
+                            global_step,
+                            accelerator.unwrap_model(text_encoder),
+                            accelerator.unwrap_model(unet),
+                            vae,
+                            logit_scale,
+                            ckpt_info,
+                            ema=ema,
+                            params_to_replace=params_to_optimize,
+                        )
+
+            current_loss = loss.detach().item()
+            if args.logging_dir is not None:
+                logs = {"loss": current_loss}
+                train_util.append_lr_to_logs(logs, lr_scheduler, args.optimizer_type, including_unet=True)
+                accelerator.log(logs, step=global_step)
+
+            loss_recorder.add(epoch=epoch, step=step, loss=current_loss)
+            avr_loss: float = loss_recorder.moving_average
+            logs = {"avr_loss": avr_loss}  # , "lr": lr_scheduler.get_last_lr()[0]}
+            progress_bar.set_postfix(**logs)
+
+            if global_step >= args.max_train_steps:
+                break
+
+        if args.logging_dir is not None:
+            logs = {"loss/epoch": loss_recorder.moving_average}
+            accelerator.log(logs, step=epoch + 1)
+
+        accelerator.wait_for_everyone()
+
+        if args.save_every_n_epochs is not None:
+            if accelerator.is_main_process:
+                # checking for saving is in util
+                src_path = src_stable_diffusion_ckpt if save_stable_diffusion_format else src_diffusers_model_path
+                train_util.save_sd_model_on_epoch_end_or_stepwise(
+                    args,
+                    True,
+                    accelerator,
+                    src_path,
+                    save_stable_diffusion_format,
+                    use_safetensors,
+                    save_dtype,
+                    epoch,
+                    num_train_epochs,
+                    global_step,
+                    accelerator.unwrap_model(text_encoder),
+                    accelerator.unwrap_model(unet),
+                    vae,
+                    logit_scale,
+                    ckpt_info,
+                    ema=ema,
+                    params_to_replace=params_to_optimize,
+                )
+
+        train_util.sample_images(accelerator, args, epoch + 1, global_step, accelerator.device, vae, tokenizer, text_encoder, unet)
+
+    is_main_process = accelerator.is_main_process
+    if is_main_process:
+        unet = accelerator.unwrap_model(unet)
+    if args.enable_ema:
+        ema = accelerator.unwrap_model(ema)
+
+    accelerator.end_training()
+
+    if args.save_state and is_main_process:
+        train_util.save_state_on_train_end(args, accelerator)
+
+    del accelerator  # この後メモリを使うのでこれは消す
+
+    if is_main_process:
+        src_path = src_stable_diffusion_ckpt if save_stable_diffusion_format else src_diffusers_model_path
+        train_util.save_sd_model_on_train_end(
+            args, src_path, save_stable_diffusion_format, use_safetensors, save_dtype, epoch, global_step, text_encoder, unet, vae
+        if args.enable_ema and not args.ema_save_only_ema_weights:
+            temp_name = args.output_name
+            args.output_name = args.output_name + "-non-EMA"
+            sdxl_train_util.save_sd_model_on_train_end(
+                args,
+                src_path,
+                save_stable_diffusion_format,
+                use_safetensors,
+                save_dtype,
+                epoch,
+                global_step,
+                text_encoder1,
+                text_encoder2,
+                unet,
+                vae,
+                logit_scale,
+                ckpt_info,
+            )
+            args.output_name = temp_name
+        if args.enable_ema:
+            print("Saving EMA:")
+            ema.copy_to(params_to_optimize)
+        )
+        print("model saved.")
+
+
+def setup_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser()
+
+    train_util.add_sd_models_arguments(parser)
+    train_util.add_dataset_arguments(parser, True, False, True)
+    train_util.add_training_arguments(parser, True)
+    train_util.add_sd_saving_arguments(parser)
+    train_util.add_optimizer_arguments(parser)
+    config_util.add_config_arguments(parser)
+    custom_train_functions.add_custom_train_arguments(parser)
+
+    parser.add_argument(
+        "--learning_rate_te",
+        type=float,
+        default=None,
+        help="learning rate for text encoder, default is same as unet / Text Encoderの学習率、デフォルトはunetと同じ",
+    )
+    parser.add_argument(
+        "--no_token_padding",
+        action="store_true",
+        help="disable token padding (same as Diffuser's DreamBooth) / トークンのpaddingを無効にする（Diffusers版DreamBoothと同じ動作）",
+    )
+    parser.add_argument(
+        "--stop_text_encoder_training",
+        type=int,
+        default=None,
+        help="steps to stop text encoder training, -1 for no training / Text Encoderの学習を止めるステップ数、-1で最初から学習しない",
+    )
+    parser.add_argument(
+        "--no_half_vae",
+        action="store_true",
+        help="do not use fp16/bf16 VAE in mixed precision (use float VAE) / mixed precisionでも fp16/bf16 VAEを使わずfloat VAEを使う",
+    )
+
+    return parser
+
+
+if __name__ == "__main__":
+    parser = setup_parser()
+
+    args = parser.parse_args()
+    args = train_util.read_config_from_file(args, parser)
+
+    train(args)