alternative impl of ControlNet-LLLite training

networks/control_net_lllite_for_train.py

@@ -0,0 +1,502 @@
+# cond_imageをU-Netのforardで渡すバージョンのControlNet-LLLite検証用実装
+# ControlNet-LLLite implementation for verification with cond_image passed in U-Net's forward
+
+import os
+import re
+from typing import Optional, List, Type
+import torch
+from library import sdxl_original_unet
+
+
+# input_blocksに適用するかどうか / if True, input_blocks are not applied
+SKIP_INPUT_BLOCKS = False
+
+# output_blocksに適用するかどうか / if True, output_blocks are not applied
+SKIP_OUTPUT_BLOCKS = True
+
+# conv2dに適用するかどうか / if True, conv2d are not applied
+SKIP_CONV2D = False
+
+# transformer_blocksのみに適用するかどうか。Trueの場合、ResBlockには適用されない
+# if True, only transformer_blocks are applied, and ResBlocks are not applied
+TRANSFORMER_ONLY = True  # if True, SKIP_CONV2D is ignored because conv2d is not used in transformer_blocks
+
+# Trueならattn1とattn2にのみ適用し、ffなどには適用しない / if True, apply only to attn1 and attn2, not to ff etc.
+ATTN1_2_ONLY = True
+
+# Trueならattn1のQKV、attn2のQにのみ適用する、ATTN1_2_ONLY指定時のみ有効 / if True, apply only to attn1 QKV and attn2 Q, only valid when ATTN1_2_ONLY is specified
+ATTN_QKV_ONLY = True
+
+# Trueならattn1やffなどにのみ適用し、attn2などには適用しない / if True, apply only to attn1 and ff, not to attn2
+# ATTN1_2_ONLYと同時にTrueにできない / cannot be True at the same time as ATTN1_2_ONLY
+ATTN1_ETC_ONLY = False  # True
+
+# transformer_blocksの最大インデックス。Noneなら全てのtransformer_blocksに適用
+# max index of transformer_blocks. if None, apply to all transformer_blocks
+TRANSFORMER_MAX_BLOCK_INDEX = None
+
+ORIGINAL_LINEAR = torch.nn.Linear
+ORIGINAL_CONV2D = torch.nn.Conv2d
+
+
+def add_lllite_modules(module: torch.nn.Module, in_dim: int, depth, cond_emb_dim, mlp_dim) -> None:
+    # conditioning1はconditioning imageを embedding する。timestepごとに呼ばれない
+    # conditioning1 embeds conditioning image. it is not called for each timestep
+    modules = []
+    modules.append(ORIGINAL_CONV2D(3, cond_emb_dim // 2, kernel_size=4, stride=4, padding=0))  # to latent (from VAE) size
+    if depth == 1:
+        modules.append(torch.nn.ReLU(inplace=True))
+        modules.append(ORIGINAL_CONV2D(cond_emb_dim // 2, cond_emb_dim, kernel_size=2, stride=2, padding=0))
+    elif depth == 2:
+        modules.append(torch.nn.ReLU(inplace=True))
+        modules.append(ORIGINAL_CONV2D(cond_emb_dim // 2, cond_emb_dim, kernel_size=4, stride=4, padding=0))
+    elif depth == 3:
+        # kernel size 8は大きすぎるので、4にする / kernel size 8 is too large, so set it to 4
+        modules.append(torch.nn.ReLU(inplace=True))
+        modules.append(ORIGINAL_CONV2D(cond_emb_dim // 2, cond_emb_dim // 2, kernel_size=4, stride=4, padding=0))
+        modules.append(torch.nn.ReLU(inplace=True))
+        modules.append(ORIGINAL_CONV2D(cond_emb_dim // 2, cond_emb_dim, kernel_size=2, stride=2, padding=0))
+
+    module.lllite_conditioning1 = torch.nn.Sequential(*modules)
+
+    # downで入力の次元数を削減する。LoRAにヒントを得ていることにする
+    # midでconditioning image embeddingと入力を結合する
+    # upで元の次元数に戻す
+    # これらはtimestepごとに呼ばれる
+    # reduce the number of input dimensions with down. inspired by LoRA
+    # combine conditioning image embedding and input with mid
+    # restore to the original dimension with up
+    # these are called for each timestep
+
+    module.lllite_down = torch.nn.Sequential(
+        ORIGINAL_LINEAR(in_dim, mlp_dim),
+        torch.nn.ReLU(inplace=True),
+    )
+    module.lllite_mid = torch.nn.Sequential(
+        ORIGINAL_LINEAR(mlp_dim + cond_emb_dim, mlp_dim),
+        torch.nn.ReLU(inplace=True),
+    )
+    module.lllite_up = torch.nn.Sequential(
+        ORIGINAL_LINEAR(mlp_dim, in_dim),
+    )
+
+    # Zero-Convにする / set to Zero-Conv
+    torch.nn.init.zeros_(module.lllite_up[0].weight)  # zero conv
+
+
+class LLLiteLinear(ORIGINAL_LINEAR):
+    def __init__(self, in_features: int, out_features: int, **kwargs):
+        super().__init__(in_features, out_features, **kwargs)
+        self.enabled = False
+
+    def set_lllite(self, depth, cond_emb_dim, name, mlp_dim, dropout=None, multiplier=1.0):
+        self.enabled = True
+        self.lllite_name = name
+        self.cond_emb_dim = cond_emb_dim
+        self.dropout = dropout
+        self.multiplier = multiplier  # ignored
+
+        in_dim = self.in_features
+        add_lllite_modules(self, in_dim, depth, cond_emb_dim, mlp_dim)
+
+        self.cond_image = None
+        self.cond_emb = None
+
+    def set_cond_image(self, cond_image):
+        self.cond_image = cond_image
+        self.cond_emb = None
+
+    def forward(self, x):
+        if not self.enabled:
+            return super().forward(x)
+
+        if self.cond_emb is None:
+            self.cond_emb = self.lllite_conditioning1(self.cond_image)
+        cx = self.cond_emb
+
+        # reshape / b,c,h,w -> b,h*w,c
+        n, c, h, w = cx.shape
+        cx = cx.view(n, c, h * w).permute(0, 2, 1)
+
+        cx = torch.cat([cx, self.lllite_down(x)], dim=2)
+        cx = self.lllite_mid(cx)
+
+        if self.dropout is not None and self.training:
+            cx = torch.nn.functional.dropout(cx, p=self.dropout)
+
+        cx = self.lllite_up(cx) * self.multiplier
+
+        x = super().forward(x + cx)  # ここで元のモジュールを呼び出す / call the original module here
+        return x
+
+
+class LLLiteConv2d(ORIGINAL_CONV2D):
+    def __init__(self, in_channels: int, out_channels: int, kernel_size, **kwargs):
+        super().__init__(in_channels, out_channels, kernel_size, **kwargs)
+        self.enabled = False
+
+    def set_lllite(self, depth, cond_emb_dim, name, mlp_dim, dropout=None, multiplier=1.0):
+        self.enabled = True
+        self.lllite_name = name
+        self.cond_emb_dim = cond_emb_dim
+        self.dropout = dropout
+        self.multiplier = multiplier  # ignored
+
+        in_dim = self.in_channels
+        add_lllite_modules(self, in_dim, depth, cond_emb_dim, mlp_dim)
+
+        self.cond_image = None
+        self.cond_emb = None
+
+    def set_cond_image(self, cond_image):
+        self.cond_image = cond_image
+        self.cond_emb = None
+
+    def forward(self, x):  # , cond_image=None):
+        if not self.enabled:
+            return super().forward(x)
+
+        if self.cond_emb is None:
+            self.cond_emb = self.lllite_conditioning1(self.cond_image)
+        cx = self.cond_emb
+
+        cx = torch.cat([cx, self.down(x)], dim=1)
+        cx = self.mid(cx)
+
+        if self.dropout is not None and self.training:
+            cx = torch.nn.functional.dropout(cx, p=self.dropout)
+
+        cx = self.up(cx) * self.multiplier
+
+        x = super().forward(x + cx)  # ここで元のモジュールを呼び出す / call the original module here
+        return x
+
+
+class SdxlUNet2DConditionModelControlNetLLLite(sdxl_original_unet.SdxlUNet2DConditionModel):
+    UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
+    UNET_TARGET_REPLACE_MODULE_CONV2D_3X3 = ["ResnetBlock2D", "Downsample2D", "Upsample2D"]
+    LLLITE_PREFIX = "lllite_unet"
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def apply_lllite(
+        self,
+        cond_emb_dim: int = 16,
+        mlp_dim: int = 16,
+        dropout: Optional[float] = None,
+        varbose: Optional[bool] = False,
+        multiplier: Optional[float] = 1.0,
+    ) -> None:
+        def apply_to_modules(
+            root_module: torch.nn.Module,
+            target_replace_modules: List[torch.nn.Module],
+        ) -> List[torch.nn.Module]:
+            prefix = "lllite_unet"
+
+            modules = []
+            for name, module in root_module.named_modules():
+                if module.__class__.__name__ in target_replace_modules:
+                    for child_name, child_module in module.named_modules():
+                        is_linear = child_module.__class__.__name__ == "LLLiteLinear"
+                        is_conv2d = child_module.__class__.__name__ == "LLLiteConv2d"
+
+                        if is_linear or (is_conv2d and not SKIP_CONV2D):
+                            # block indexからdepthを計算: depthはconditioningのサイズやチャネルを計算するのに使う
+                            # block index to depth: depth is using to calculate conditioning size and channels
+                            block_name, index1, index2 = (name + "." + child_name).split(".")[:3]
+                            index1 = int(index1)
+                            if block_name == "input_blocks":
+                                if SKIP_INPUT_BLOCKS:
+                                    continue
+                                depth = 1 if index1 <= 2 else (2 if index1 <= 5 else 3)
+                            elif block_name == "middle_block":
+                                depth = 3
+                            elif block_name == "output_blocks":
+                                if SKIP_OUTPUT_BLOCKS:
+                                    continue
+                                depth = 3 if index1 <= 2 else (2 if index1 <= 5 else 1)
+                                if int(index2) >= 2:
+                                    depth -= 1
+                            else:
+                                raise NotImplementedError()
+
+                            lllite_name = prefix + "." + name + "." + child_name
+                            lllite_name = lllite_name.replace(".", "_")
+
+                            if TRANSFORMER_MAX_BLOCK_INDEX is not None:
+                                p = lllite_name.find("transformer_blocks")
+                                if p >= 0:
+                                    tf_index = int(lllite_name[p:].split("_")[2])
+                                    if tf_index > TRANSFORMER_MAX_BLOCK_INDEX:
+                                        continue
+
+                            #  time embは適用外とする
+                            # attn2のconditioning (CLIPからの入力) はshapeが違うので適用できない
+                            # time emb is not applied
+                            # attn2 conditioning (input from CLIP) cannot be applied because the shape is different
+                            if "emb_layers" in lllite_name or (
+                                "attn2" in lllite_name and ("to_k" in lllite_name or "to_v" in lllite_name)
+                            ):
+                                continue
+
+                            if ATTN1_2_ONLY:
+                                if not ("attn1" in lllite_name or "attn2" in lllite_name):
+                                    continue
+                                if ATTN_QKV_ONLY:
+                                    if "to_out" in lllite_name:
+                                        continue
+
+                            if ATTN1_ETC_ONLY:
+                                if "proj_out" in lllite_name:
+                                    pass
+                                elif "attn1" in lllite_name and (
+                                    "to_k" in lllite_name or "to_v" in lllite_name or "to_out" in lllite_name
+                                ):
+                                    pass
+                                elif "ff_net_2" in lllite_name:
+                                    pass
+                                else:
+                                    continue
+
+                            child_module.set_lllite(depth, cond_emb_dim, lllite_name, mlp_dim, dropout, multiplier)
+                            modules.append(child_module)
+
+            return modules
+
+        target_modules = SdxlUNet2DConditionModelControlNetLLLite.UNET_TARGET_REPLACE_MODULE
+        if not TRANSFORMER_ONLY:
+            target_modules = target_modules + SdxlUNet2DConditionModelControlNetLLLite.UNET_TARGET_REPLACE_MODULE_CONV2D_3X3
+
+        # create module instances
+        self.lllite_modules = apply_to_modules(self, target_modules)
+        print(f"enable ControlNet LLLite for U-Net: {len(self.lllite_modules)} modules.")
+
+    # def prepare_optimizer_params(self):
+    def prepare_params(self):
+        train_params = []
+        non_train_params = []
+        for name, p in self.named_parameters():
+            if "lllite" in name:
+                train_params.append(p)
+            else:
+                non_train_params.append(p)
+        print(f"count of trainable parameters: {len(train_params)}")
+        print(f"count of non-trainable parameters: {len(non_train_params)}")
+
+        for p in non_train_params:
+            p.requires_grad_(False)
+
+        # without this, an error occurs in the optimizer
+        #       RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn
+        non_train_params[0].requires_grad_(True)
+
+        for p in train_params:
+            p.requires_grad_(True)
+
+        return train_params
+
+    # def prepare_grad_etc(self):
+    #     self.requires_grad_(True)
+
+    # def on_epoch_start(self):
+    #     self.train()
+
+    def get_trainable_params(self):
+        return [p[1] for p in self.named_parameters() if "lllite" in p[0]]
+
+    def save_lllite_weights(self, file, dtype, metadata):
+        if metadata is not None and len(metadata) == 0:
+            metadata = None
+
+        org_state_dict = self.state_dict()
+
+        # copy LLLite keys from org_state_dict to state_dict with key conversion
+        state_dict = {}
+        for key in org_state_dict.keys():
+            # split with ".lllite"
+            pos = key.find(".lllite")
+            if pos < 0:
+                continue
+            lllite_key = SdxlUNet2DConditionModelControlNetLLLite.LLLITE_PREFIX + "." + key[:pos]
+            lllite_key = lllite_key.replace(".", "_") + key[pos:]
+            lllite_key = lllite_key.replace(".lllite_", ".")
+            state_dict[lllite_key] = org_state_dict[key]
+
+        if dtype is not None:
+            for key in list(state_dict.keys()):
+                v = state_dict[key]
+                v = v.detach().clone().to("cpu").to(dtype)
+                state_dict[key] = v
+
+        if os.path.splitext(file)[1] == ".safetensors":
+            from safetensors.torch import save_file
+
+            save_file(state_dict, file, metadata)
+        else:
+            torch.save(state_dict, file)
+
+    def load_lllite_weights(self, file, non_lllite_unet_sd=None):
+        r"""
+        LLLiteの重みを読み込まない（initされた値を使う）場合はfileにNoneを指定する。
+        この場合、non_lllite_unet_sdにはU-Netのstate_dictを指定する。
+
+        If you do not want to load LLLite weights (use initialized values), specify None for file.
+        In this case, specify the state_dict of U-Net for non_lllite_unet_sd.
+        """
+        if not file:
+            state_dict = self.state_dict()
+            for key in non_lllite_unet_sd:
+                if key in state_dict:
+                    state_dict[key] = non_lllite_unet_sd[key]
+            info = self.load_state_dict(state_dict, False)
+            return info
+
+        if os.path.splitext(file)[1] == ".safetensors":
+            from safetensors.torch import load_file
+
+            weights_sd = load_file(file)
+        else:
+            weights_sd = torch.load(file, map_location="cpu")
+
+        # module_name = module_name.replace("_block", "@blocks")
+        # module_name = module_name.replace("_layer", "@layer")
+        # module_name = module_name.replace("to_", "to@")
+        # module_name = module_name.replace("time_embed", "time@embed")
+        # module_name = module_name.replace("label_emb", "label@emb")
+        # module_name = module_name.replace("skip_connection", "skip@connection")
+        # module_name = module_name.replace("proj_in", "proj@in")
+        # module_name = module_name.replace("proj_out", "proj@out")
+        pattern = re.compile(r"(_block|_layer|to_|time_embed|label_emb|skip_connection|proj_in|proj_out)")
+
+        # conver to lllite with U-Net state dict
+        state_dict = non_lllite_unet_sd.copy() if non_lllite_unet_sd is not None else {}
+        for key in weights_sd.keys():
+            # split with "."
+            pos = key.find(".")
+            if pos < 0:
+                continue
+
+            module_name = key[:pos]
+            weight_name = key[pos + 1 :]  # exclude "."
+            module_name = module_name.replace(SdxlUNet2DConditionModelControlNetLLLite.LLLITE_PREFIX + "_", "")
+
+            # これはうまくいかない。逆変換を考えなかった設計が悪い / this does not work well. bad design because I didn't think about inverse conversion
+            # module_name = module_name.replace("_", ".")
+
+            # ださいけどSDXLのU-Netの "_" を "@" に変換する / ugly but convert "_" of SDXL U-Net to "@"
+            matches = pattern.findall(module_name)
+            if matches is not None:
+                for m in matches:
+                    print(module_name, m)
+                    module_name = module_name.replace(m, m.replace("_", "@"))
+            module_name = module_name.replace("_", ".")
+            module_name = module_name.replace("@", "_")
+
+            lllite_key = module_name + ".lllite_" + weight_name
+
+            state_dict[lllite_key] = weights_sd[key]
+
+        info = self.load_state_dict(state_dict, False)
+        return info
+
+    def forward(self, x, timesteps=None, context=None, y=None, cond_image=None, **kwargs):
+        for m in self.lllite_modules:
+            m.set_cond_image(cond_image)
+        return super().forward(x, timesteps, context, y, **kwargs)
+
+
+def replace_unet_linear_and_conv2d():
+    print("replace torch.nn.Linear and torch.nn.Conv2d to LLLiteLinear and LLLiteConv2d in U-Net")
+    sdxl_original_unet.torch.nn.Linear = LLLiteLinear
+    sdxl_original_unet.torch.nn.Conv2d = LLLiteConv2d
+
+
+if __name__ == "__main__":
+    # デバッグ用 / for debug
+
+    # sdxl_original_unet.USE_REENTRANT = False
+    replace_unet_linear_and_conv2d()
+
+    # test shape etc
+    print("create unet")
+    unet = SdxlUNet2DConditionModelControlNetLLLite()
+
+    print("enable ControlNet-LLLite")
+    unet.apply_lllite(32, 64, None, False, 1.0)
+    unet.to("cuda")  # .to(torch.float16)
+
+    # from safetensors.torch import load_file
+
+    # model_sd = load_file(r"E:\Work\SD\Models\sdxl\sd_xl_base_1.0_0.9vae.safetensors")
+    # unet_sd = {}
+
+    # # copy U-Net keys from unet_state_dict to state_dict
+    # prefix = "model.diffusion_model."
+    # for key in model_sd.keys():
+    #     if key.startswith(prefix):
+    #         converted_key = key[len(prefix) :]
+    #         unet_sd[converted_key] = model_sd[key]
+
+    # info = unet.load_lllite_weights("r:/lllite_from_unet.safetensors", unet_sd)
+    # print(info)
+
+    # print(unet)
+
+    # print number of parameters
+    params = unet.prepare_params()
+    print("number of parameters", sum(p.numel() for p in params))
+    # print("type any key to continue")
+    # input()
+
+    unet.set_use_memory_efficient_attention(True, False)
+    unet.set_gradient_checkpointing(True)
+    unet.train()  # for gradient checkpointing
+
+    # # visualize
+    # import torchviz
+    # print("run visualize")
+    # controlnet.set_control(conditioning_image)
+    # output = unet(x, t, ctx, y)
+    # print("make_dot")
+    # image = torchviz.make_dot(output, params=dict(controlnet.named_parameters()))
+    # print("render")
+    # image.format = "svg" # "png"
+    # image.render("NeuralNet") # すごく時間がかかるので注意 / be careful because it takes a long time
+    # input()
+
+    import bitsandbytes
+
+    optimizer = bitsandbytes.adam.Adam8bit(params, 1e-3)
+
+    scaler = torch.cuda.amp.GradScaler(enabled=True)
+
+    print("start training")
+    steps = 10
+    batch_size = 1
+
+    sample_param = [p for p in unet.named_parameters() if ".lllite_up." in p[0]][0]
+    for step in range(steps):
+        print(f"step {step}")
+
+        conditioning_image = torch.rand(batch_size, 3, 1024, 1024).cuda() * 2.0 - 1.0
+        x = torch.randn(batch_size, 4, 128, 128).cuda()
+        t = torch.randint(low=0, high=10, size=(batch_size,)).cuda()
+        ctx = torch.randn(batch_size, 77, 2048).cuda()
+        y = torch.randn(batch_size, sdxl_original_unet.ADM_IN_CHANNELS).cuda()
+
+        with torch.cuda.amp.autocast(enabled=True, dtype=torch.bfloat16):
+            output = unet(x, t, ctx, y, conditioning_image)
+            target = torch.randn_like(output)
+            loss = torch.nn.functional.mse_loss(output, target)
+
+        scaler.scale(loss).backward()
+        scaler.step(optimizer)
+        scaler.update()
+        optimizer.zero_grad(set_to_none=True)
+        print(sample_param)
+
+    # from safetensors.torch import save_file
+
+    # print("save weights")
+    # unet.save_lllite_weights("r:/lllite_from_unet.safetensors", torch.float16, None)

sdxl_train_control_net_lllite_alt.py

@@ -0,0 +1,602 @@
+# cond_imageをU-Netのforardで渡すバージョンのControlNet-LLLite検証用学習コード
+# training code for ControlNet-LLLite with passing cond_image to U-Net's forward
+
+import argparse
+import gc
+import json
+import math
+import os
+import random
+import time
+from multiprocessing import Value
+from types import SimpleNamespace
+import toml
+
+from tqdm import tqdm
+import torch
+from torch.nn.parallel import DistributedDataParallel as DDP
+from accelerate.utils import set_seed
+import accelerate
+from diffusers import DDPMScheduler, ControlNetModel
+from safetensors.torch import load_file
+from library import sai_model_spec, sdxl_model_util, sdxl_original_unet, sdxl_train_util
+
+import library.model_util as model_util
+import library.train_util as train_util
+import library.config_util as config_util
+from library.config_util import (
+    ConfigSanitizer,
+    BlueprintGenerator,
+)
+import library.huggingface_util as huggingface_util
+import library.custom_train_functions as custom_train_functions
+from library.custom_train_functions import (
+    add_v_prediction_like_loss,
+    apply_snr_weight,
+    prepare_scheduler_for_custom_training,
+    pyramid_noise_like,
+    apply_noise_offset,
+    scale_v_prediction_loss_like_noise_prediction,
+)
+import networks.control_net_lllite_for_train as control_net_lllite_for_train
+
+
+# TODO 他のスクリプトと共通化する
+def generate_step_logs(args: argparse.Namespace, current_loss, avr_loss, lr_scheduler):
+    logs = {
+        "loss/current": current_loss,
+        "loss/average": avr_loss,
+        "lr": lr_scheduler.get_last_lr()[0],
+    }
+
+    if args.optimizer_type.lower().startswith("DAdapt".lower()):
+        logs["lr/d*lr"] = lr_scheduler.optimizers[-1].param_groups[0]["d"] * lr_scheduler.optimizers[-1].param_groups[0]["lr"]
+
+    return logs
+
+
+def train(args):
+    train_util.verify_training_args(args)
+    train_util.prepare_dataset_args(args, True)
+    sdxl_train_util.verify_sdxl_training_args(args)
+
+    cache_latents = args.cache_latents
+    use_user_config = args.dataset_config is not None
+
+    if args.seed is None:
+        args.seed = random.randint(0, 2**32)
+    set_seed(args.seed)
+
+    tokenizer1, tokenizer2 = sdxl_train_util.load_tokenizers(args)
+
+    # データセットを準備する
+    blueprint_generator = BlueprintGenerator(ConfigSanitizer(False, False, True, True))
+    if use_user_config:
+        print(f"Load dataset config from {args.dataset_config}")
+        user_config = config_util.load_user_config(args.dataset_config)
+        ignored = ["train_data_dir", "conditioning_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_controlnet_subsets_config_by_subdirs(
+                        args.train_data_dir,
+                        args.conditioning_data_dir,
+                        args.caption_extension,
+                    )
+                }
+            ]
+        }
+
+    blueprint = blueprint_generator.generate(user_config, args, tokenizer=[tokenizer1, tokenizer2])
+    train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
+
+    current_epoch = Value("i", 0)
+    current_step = Value("i", 0)
+    ds_for_collater = train_dataset_group if args.max_data_loader_n_workers == 0 else None
+    collater = train_util.collater_class(current_epoch, current_step, ds_for_collater)
+
+    train_dataset_group.verify_bucket_reso_steps(32)
+
+    if args.debug_dataset:
+        train_util.debug_dataset(train_dataset_group)
+        return
+    if len(train_dataset_group) == 0:
+        print(
+            "No data found. Please verify arguments (train_data_dir must be the parent of folders with images) / 画像がありません。引数指定を確認してください（train_data_dirには画像があるフォルダではなく、画像があるフォルダの親フォルダを指定する必要があります）"
+        )
+        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"
+    else:
+        print("WARNING: random_crop is not supported yet for ControlNet training / ControlNetの学習ではrandom_cropはまだサポートされていません")
+
+    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)
+    is_main_process = accelerator.is_main_process
+
+    # 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_model_util.MODEL_VERSION_SDXL_BASE_V1_0, weight_dtype)
+
+    # 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()
+
+    # 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():
+            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()
+
+    # prepare ControlNet-LLLite
+    control_net_lllite_for_train.replace_unet_linear_and_conv2d()
+
+    if args.network_weights is not None:
+        accelerator.print(f"initialize U-Net with ControlNet-LLLite")
+        with accelerate.init_empty_weights():
+            unet_lllite = control_net_lllite_for_train.SdxlUNet2DConditionModelControlNetLLLite()
+        unet_lllite.to(accelerator.device, dtype=weight_dtype)
+
+        unet_sd = unet.state_dict()
+        info = unet_lllite.load_lllite_weights(args.network_weights, unet_sd)
+        accelerator.print(f"load ControlNet-LLLite weights from {args.network_weights}: {info}")
+    else:
+        # cosumes large memory, so send to GPU before creating the LLLite model
+        accelerator.print("sending U-Net to GPU")
+        unet.to(accelerator.device, dtype=weight_dtype)
+        unet_sd = unet.state_dict()
+
+        # init LLLite weights
+        accelerator.print(f"initialize U-Net with ControlNet-LLLite")
+
+        if args.lowram:
+            with accelerate.init_on_device(accelerator.device):
+                unet_lllite = control_net_lllite_for_train.SdxlUNet2DConditionModelControlNetLLLite()
+        else:
+            unet_lllite = control_net_lllite_for_train.SdxlUNet2DConditionModelControlNetLLLite()
+        unet_lllite.to(weight_dtype)
+
+        info = unet_lllite.load_lllite_weights(None, unet_sd)
+        accelerator.print(f"init U-Net with ControlNet-LLLite weights: {info}")
+    del unet_sd, unet
+
+    unet: control_net_lllite_for_train.SdxlUNet2DConditionModelControlNetLLLite = unet_lllite
+    del unet_lllite
+
+    unet.apply_lllite(args.cond_emb_dim, args.network_dim, args.network_dropout)
+
+    # 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)
+
+    if args.gradient_checkpointing:
+        unet.enable_gradient_checkpointing()
+
+    # 学習に必要なクラスを準備する
+    accelerator.print("prepare optimizer, data loader etc.")
+
+    trainable_params = list(unet.prepare_params())
+    print(f"trainable params count: {len(trainable_params)}")
+    print(f"number of trainable parameters: {sum(p.numel() for p in trainable_params if p.requires_grad)}")
+
+    _, _, 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=collater,
+        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)
+    # 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)
+
+    unet.to(weight_dtype)
+
+    # acceleratorがなんかよろしくやってくれるらしい
+    unet, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(unet, optimizer, train_dataloader, lr_scheduler)
+
+    # transform DDP after prepare (train_network here only)
+    unet = train_util.transform_models_if_DDP([unet])[0]
+
+    if args.gradient_checkpointing:
+        unet.train()  # according to TI example in Diffusers, train is required -> これオリジナルのU-Netしたので本当は外せる
+    else:
+        unet.eval()
+
+    # 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)
+
+    if not cache_latents:
+        vae.requires_grad_(False)
+        vae.eval()
+        vae.to(accelerator.device, dtype=vae_dtype)
+
+    # 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
+    # TODO: find a way to handle total batch size when there are multiple datasets
+    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: {', '.join([str(d.batch_size) for d in train_dataset_group.datasets])}")
+    # 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.log_tracker_config is not None:
+            init_kwargs = toml.load(args.log_tracker_config)
+        accelerator.init_trackers(
+            "lllite_control_net_train" if args.log_tracker_name is None else args.log_tracker_name, init_kwargs=init_kwargs
+        )
+
+    loss_list = []
+    loss_total = 0.0
+    del train_dataset_group
+
+    # function for saving/removing
+    def save_model(
+        ckpt_name,
+        unwrapped_nw: control_net_lllite_for_train.SdxlUNet2DConditionModelControlNetLLLite,
+        steps,
+        epoch_no,
+        force_sync_upload=False,
+    ):
+        os.makedirs(args.output_dir, exist_ok=True)
+        ckpt_file = os.path.join(args.output_dir, ckpt_name)
+
+        accelerator.print(f"\nsaving checkpoint: {ckpt_file}")
+        sai_metadata = train_util.get_sai_model_spec(None, args, True, True, False)
+        sai_metadata["modelspec.architecture"] = sai_model_spec.ARCH_SD_XL_V1_BASE + "/control-net-lllite"
+
+        unwrapped_nw.save_lllite_weights(ckpt_file, save_dtype, sai_metadata)
+        if args.huggingface_repo_id is not None:
+            huggingface_util.upload(args, ckpt_file, "/" + ckpt_name, force_sync_upload=force_sync_upload)
+
+    def remove_model(old_ckpt_name):
+        old_ckpt_file = os.path.join(args.output_dir, old_ckpt_name)
+        if os.path.exists(old_ckpt_file):
+            accelerator.print(f"removing old checkpoint: {old_ckpt_file}")
+            os.remove(old_ckpt_file)
+
+    # training loop
+    for epoch in range(num_train_epochs):
+        accelerator.print(f"\nepoch {epoch+1}/{num_train_epochs}")
+        current_epoch.value = epoch + 1
+
+        for step, batch in enumerate(train_dataloader):
+            current_step.value = global_step
+            with accelerator.accumulate(unet):
+                with torch.no_grad():
+                    if "latents" in batch and batch["latents"] is not None:
+                        latents = batch["latents"].to(accelerator.device)
+                    else:
+                        # latentに変換
+                        latents = vae.encode(batch["images"].to(dtype=vae_dtype)).latent_dist.sample()
+
+                        # 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.where(torch.isnan(latents), torch.zeros_like(latents), 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.no_grad():
+                        # Get the text embedding for conditioning
+                        input_ids1 = input_ids1.to(accelerator.device)
+                        input_ids2 = input_ids2.to(accelerator.device)
+                        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,
+                        )
+                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)
+
+                # 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
+
+                controlnet_image = batch["conditioning_images"].to(dtype=weight_dtype)
+
+                with accelerator.autocast():
+                    # conditioning imageをControlNetに渡す / pass conditioning image to ControlNet
+                    # 内部でcond_embに変換される / it will be converted to cond_emb inside
+
+                    # それらの値を使いつつ、U-Netでノイズを予測する / predict noise with U-Net using those values
+                    noise_pred = unet(noisy_latents, timesteps, text_embedding, vector_embedding, controlnet_image)
+
+                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)
+                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)
+
+                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:
+                    params_to_clip = unet.get_trainable_params()
+                    accelerator.clip_grad_norm_(params_to_clip, args.max_grad_norm)
+
+                optimizer.step()
+                lr_scheduler.step()
+                optimizer.zero_grad(set_to_none=True)
+
+            # 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, 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:
+                        ckpt_name = train_util.get_step_ckpt_name(args, "." + args.save_model_as, global_step)
+                        save_model(ckpt_name, accelerator.unwrap_model(unet), global_step, epoch)
+
+                        if args.save_state:
+                            train_util.save_and_remove_state_stepwise(args, accelerator, global_step)
+
+                        remove_step_no = train_util.get_remove_step_no(args, global_step)
+                        if remove_step_no is not None:
+                            remove_ckpt_name = train_util.get_step_ckpt_name(args, "." + args.save_model_as, remove_step_no)
+                            remove_model(remove_ckpt_name)
+
+            current_loss = loss.detach().item()
+            if epoch == 0:
+                loss_list.append(current_loss)
+            else:
+                loss_total -= loss_list[step]
+                loss_list[step] = current_loss
+            loss_total += current_loss
+            avr_loss = loss_total / len(loss_list)
+            logs = {"loss": avr_loss}  # , "lr": lr_scheduler.get_last_lr()[0]}
+            progress_bar.set_postfix(**logs)
+
+            if args.logging_dir is not None:
+                logs = generate_step_logs(args, current_loss, avr_loss, lr_scheduler)
+                accelerator.log(logs, step=global_step)
+
+            if global_step >= args.max_train_steps:
+                break
+
+        if args.logging_dir is not None:
+            logs = {"loss/epoch": loss_total / len(loss_list)}
+            accelerator.log(logs, step=epoch + 1)
+
+        accelerator.wait_for_everyone()
+
+        # 指定エポックごとにモデルを保存
+        if args.save_every_n_epochs is not None:
+            saving = (epoch + 1) % args.save_every_n_epochs == 0 and (epoch + 1) < num_train_epochs
+            if is_main_process and saving:
+                ckpt_name = train_util.get_epoch_ckpt_name(args, "." + args.save_model_as, epoch + 1)
+                save_model(ckpt_name, accelerator.unwrap_model(unet), global_step, epoch + 1)
+
+                remove_epoch_no = train_util.get_remove_epoch_no(args, epoch + 1)
+                if remove_epoch_no is not None:
+                    remove_ckpt_name = train_util.get_epoch_ckpt_name(args, "." + args.save_model_as, remove_epoch_no)
+                    remove_model(remove_ckpt_name)
+
+                if args.save_state:
+                    train_util.save_and_remove_state_on_epoch_end(args, accelerator, epoch + 1)
+
+        # self.sample_images(accelerator, args, epoch + 1, global_step, accelerator.device, vae, tokenizer, text_encoder, unet)
+
+        # end of epoch
+
+    if is_main_process:
+        unet = accelerator.unwrap_model(unet)
+
+    accelerator.end_training()
+
+    if is_main_process and args.save_state:
+        train_util.save_state_on_train_end(args, accelerator)
+
+    if is_main_process:
+        ckpt_name = train_util.get_last_ckpt_name(args, "." + args.save_model_as)
+        save_model(ckpt_name, unet, global_step, num_train_epochs, force_sync_upload=True)
+
+        print("model saved.")
+
+
+def setup_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser()
+
+    train_util.add_sd_models_arguments(parser)
+    train_util.add_dataset_arguments(parser, False, True, True)
+    train_util.add_training_arguments(parser, False)
+    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(
+        "--save_model_as",
+        type=str,
+        default="safetensors",
+        choices=[None, "ckpt", "pt", "safetensors"],
+        help="format to save the model (default is .safetensors) / モデル保存時の形式（デフォルトはsafetensors）",
+    )
+    parser.add_argument("--cond_emb_dim", type=int, default=None, help="conditioning embedding dimension / 条件付け埋め込みの次元数")
+    parser.add_argument("--network_weights", type=str, default=None, help="pretrained weights for network / 学習するネットワークの初期重み")
+    parser.add_argument("--network_dim", type=int, default=None, help="network dimensions (rank) / モジュールの次元数")
+    parser.add_argument(
+        "--network_dropout",
+        type=float,
+        default=None,
+        help="Drops neurons out of training every step (0 or None is default behavior (no dropout), 1 would drop all neurons) / 訓練時に毎ステップでニューロンをdropする（0またはNoneはdropoutなし、1は全ニューロンをdropout）",
+    )
+    parser.add_argument(
+        "--conditioning_data_dir",
+        type=str,
+        default=None,
+        help="conditioning data directory / 条件付けデータのディレクトリ",
+    )
+    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__":
+    # sdxl_original_unet.USE_REENTRANT = False
+
+    parser = setup_parser()
+
+    args = parser.parse_args()
+    args = train_util.read_config_from_file(args, parser)
+
+    train(args)