Implement XTI

XTI_hijack.py

@@ -0,0 +1,209 @@
+import torch
+from typing import Union, List, Optional, Dict, Any, Tuple
+from diffusers.models.unet_2d_condition import UNet2DConditionOutput
+
+def unet_forward_XTI(self,
+        sample: torch.FloatTensor,
+        timestep: Union[torch.Tensor, float, int],
+        encoder_hidden_states: torch.Tensor,
+        class_labels: Optional[torch.Tensor] = None,
+        return_dict: bool = True,
+    ) -> Union[UNet2DConditionOutput, Tuple]:
+        r"""
+        Args:
+            sample (`torch.FloatTensor`): (batch, channel, height, width) noisy inputs tensor
+            timestep (`torch.FloatTensor` or `float` or `int`): (batch) timesteps
+            encoder_hidden_states (`torch.FloatTensor`): (batch, sequence_length, feature_dim) encoder hidden states
+            return_dict (`bool`, *optional*, defaults to `True`):
+                Whether or not to return a [`models.unet_2d_condition.UNet2DConditionOutput`] instead of a plain tuple.
+
+        Returns:
+            [`~models.unet_2d_condition.UNet2DConditionOutput`] or `tuple`:
+            [`~models.unet_2d_condition.UNet2DConditionOutput`] if `return_dict` is True, otherwise a `tuple`. When
+            returning a tuple, the first element is the sample tensor.
+        """
+        # By default samples have to be AT least a multiple of the overall upsampling factor.
+        # The overall upsampling factor is equal to 2 ** (# num of upsampling layears).
+        # However, the upsampling interpolation output size can be forced to fit any upsampling size
+        # on the fly if necessary.
+        default_overall_up_factor = 2**self.num_upsamplers
+
+        # upsample size should be forwarded when sample is not a multiple of `default_overall_up_factor`
+        forward_upsample_size = False
+        upsample_size = None
+
+        if any(s % default_overall_up_factor != 0 for s in sample.shape[-2:]):
+            logger.info("Forward upsample size to force interpolation output size.")
+            forward_upsample_size = True
+
+        # 0. center input if necessary
+        if self.config.center_input_sample:
+            sample = 2 * sample - 1.0
+
+        # 1. time
+        timesteps = timestep
+        if not torch.is_tensor(timesteps):
+            # TODO: this requires sync between CPU and GPU. So try to pass timesteps as tensors if you can
+            # This would be a good case for the `match` statement (Python 3.10+)
+            is_mps = sample.device.type == "mps"
+            if isinstance(timestep, float):
+                dtype = torch.float32 if is_mps else torch.float64
+            else:
+                dtype = torch.int32 if is_mps else torch.int64
+            timesteps = torch.tensor([timesteps], dtype=dtype, device=sample.device)
+        elif len(timesteps.shape) == 0:
+            timesteps = timesteps[None].to(sample.device)
+
+        # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
+        timesteps = timesteps.expand(sample.shape[0])
+
+        t_emb = self.time_proj(timesteps)
+
+        # timesteps does not contain any weights and will always return f32 tensors
+        # but time_embedding might actually be running in fp16. so we need to cast here.
+        # there might be better ways to encapsulate this.
+        t_emb = t_emb.to(dtype=self.dtype)
+        emb = self.time_embedding(t_emb)
+
+        if self.config.num_class_embeds is not None:
+            if class_labels is None:
+                raise ValueError("class_labels should be provided when num_class_embeds > 0")
+            class_emb = self.class_embedding(class_labels).to(dtype=self.dtype)
+            emb = emb + class_emb
+
+        # 2. pre-process
+        sample = self.conv_in(sample)
+
+        # 3. down
+        down_block_res_samples = (sample,)
+        down_i = 0
+        for downsample_block in self.down_blocks:
+            if hasattr(downsample_block, "has_cross_attention") and downsample_block.has_cross_attention:
+                sample, res_samples = downsample_block(
+                    hidden_states=sample,
+                    temb=emb,
+                    encoder_hidden_states=encoder_hidden_states[down_i:down_i+2],
+                )
+                down_i += 2
+            else:
+                sample, res_samples = downsample_block(hidden_states=sample, temb=emb)
+
+            down_block_res_samples += res_samples
+
+        # 4. mid
+        sample = self.mid_block(sample, emb, encoder_hidden_states=encoder_hidden_states[6])
+
+        # 5. up
+        up_i = 7
+        for i, upsample_block in enumerate(self.up_blocks):
+            is_final_block = i == len(self.up_blocks) - 1
+
+            res_samples = down_block_res_samples[-len(upsample_block.resnets) :]
+            down_block_res_samples = down_block_res_samples[: -len(upsample_block.resnets)]
+
+            # if we have not reached the final block and need to forward the
+            # upsample size, we do it here
+            if not is_final_block and forward_upsample_size:
+                upsample_size = down_block_res_samples[-1].shape[2:]
+
+            if hasattr(upsample_block, "has_cross_attention") and upsample_block.has_cross_attention:
+                sample = upsample_block(
+                    hidden_states=sample,
+                    temb=emb,
+                    res_hidden_states_tuple=res_samples,
+                    encoder_hidden_states=encoder_hidden_states[up_i:up_i+3],
+                    upsample_size=upsample_size,
+                )
+                up_i += 3
+            else:
+                sample = upsample_block(
+                    hidden_states=sample, temb=emb, res_hidden_states_tuple=res_samples, upsample_size=upsample_size
+                )
+        # 6. post-process
+        sample = self.conv_norm_out(sample)
+        sample = self.conv_act(sample)
+        sample = self.conv_out(sample)
+
+        if not return_dict:
+            return (sample,)
+
+        return UNet2DConditionOutput(sample=sample)
+
+def downblock_forward_XTI(
+    self, hidden_states, temb=None, encoder_hidden_states=None, attention_mask=None, cross_attention_kwargs=None
+):
+    output_states = ()
+    i = 0
+
+    for resnet, attn in zip(self.resnets, self.attentions):
+        if self.training and self.gradient_checkpointing:
+
+            def create_custom_forward(module, return_dict=None):
+                def custom_forward(*inputs):
+                    if return_dict is not None:
+                        return module(*inputs, return_dict=return_dict)
+                    else:
+                        return module(*inputs)
+
+                return custom_forward
+
+            hidden_states = torch.utils.checkpoint.checkpoint(create_custom_forward(resnet), hidden_states, temb)
+            hidden_states = torch.utils.checkpoint.checkpoint(
+                create_custom_forward(attn, return_dict=False), hidden_states, encoder_hidden_states[i]
+            )[0]
+        else:
+            hidden_states = resnet(hidden_states, temb)
+            hidden_states = attn(hidden_states, encoder_hidden_states=encoder_hidden_states[i]).sample
+
+        output_states += (hidden_states,)
+        i += 1
+
+    if self.downsamplers is not None:
+        for downsampler in self.downsamplers:
+            hidden_states = downsampler(hidden_states)
+
+        output_states += (hidden_states,)
+
+    return hidden_states, output_states
+
+def upblock_forward_XTI(
+    self,
+    hidden_states,
+    res_hidden_states_tuple,
+    temb=None,
+    encoder_hidden_states=None,
+    upsample_size=None,
+):
+    i = 0
+    for resnet, attn in zip(self.resnets, self.attentions):
+        # pop res hidden states
+        res_hidden_states = res_hidden_states_tuple[-1]
+        res_hidden_states_tuple = res_hidden_states_tuple[:-1]
+        hidden_states = torch.cat([hidden_states, res_hidden_states], dim=1)
+
+        if self.training and self.gradient_checkpointing:
+
+            def create_custom_forward(module, return_dict=None):
+                def custom_forward(*inputs):
+                    if return_dict is not None:
+                        return module(*inputs, return_dict=return_dict)
+                    else:
+                        return module(*inputs)
+
+                return custom_forward
+
+            hidden_states = torch.utils.checkpoint.checkpoint(create_custom_forward(resnet), hidden_states, temb)
+            hidden_states = torch.utils.checkpoint.checkpoint(
+                create_custom_forward(attn, return_dict=False), hidden_states, encoder_hidden_states[i]
+            )[0]
+        else:
+            hidden_states = resnet(hidden_states, temb)
+            hidden_states = attn(hidden_states, encoder_hidden_states=encoder_hidden_states[i]).sample
+        
+        i += 1
+
+    if self.upsamplers is not None:
+        for upsampler in self.upsamplers:
+            hidden_states = upsampler(hidden_states, upsample_size)
+
+    return hidden_states

gen_img_diffusers.py

@@ -84,6 +84,8 @@ import library.train_util as train_util
 import tools.original_control_net as original_control_net
 from tools.original_control_net import ControlNetInfo
 
+from XTI_hijack import unet_forward_XTI, downblock_forward_XTI, upblock_forward_XTI
+
 # Tokenizer: checkpointから読み込むのではなくあらかじめ提供されているものを使う
 TOKENIZER_PATH = "openai/clip-vit-large-patch14"
 V2_STABLE_DIFFUSION_PATH = "stabilityai/stable-diffusion-2"     # ここからtokenizerだけ使う
@@ -475,6 +477,9 @@ class PipelineLike():
     # Textual Inversion
     self.token_replacements = {}
 
+    # XTI
+    self.token_replacements_XTI = {}
+
     # CLIP guidance
     self.clip_guidance_scale = clip_guidance_scale
     self.clip_image_guidance_scale = clip_image_guidance_scale
@@ -496,15 +501,26 @@ class PipelineLike():
   def add_token_replacement(self, target_token_id, rep_token_ids):
     self.token_replacements[target_token_id] = rep_token_ids
 
-  def replace_token(self, tokens):
+  def replace_token(self, tokens, layer=None):
     new_tokens = []
     for token in tokens:
       if token in self.token_replacements:
-        new_tokens.extend(self.token_replacements[token])
+        replacer_ = self.token_replacements[token]
+        if layer:
+          replacer = []
+          for r in replacer_:
+            if r in self.token_replacements_XTI:
+              replacer.append(self.token_replacements_XTI[r][layer])
+        else:
+          replacer = replacer_
+        new_tokens.extend(replacer)
       else:
         new_tokens.append(token)
     return new_tokens
 
+  def add_token_replacement_XTI(self, target_token_id, rep_token_ids):
+    self.token_replacements_XTI[target_token_id] = rep_token_ids
+
   def set_control_nets(self, ctrl_nets):
     self.control_nets = ctrl_nets
 
@@ -723,14 +739,15 @@ class PipelineLike():
           " the batch size of `prompt`."
       )
 
-    text_embeddings, uncond_embeddings, prompt_tokens = get_weighted_text_embeddings(
-        pipe=self,
-        prompt=prompt,
-        uncond_prompt=negative_prompt if do_classifier_free_guidance else None,
-        max_embeddings_multiples=max_embeddings_multiples,
-        clip_skip=self.clip_skip,
-        **kwargs,
-    )
+    if not args.XTI_embeddings:
+      text_embeddings, uncond_embeddings, prompt_tokens = get_weighted_text_embeddings(
+          pipe=self,
+          prompt=prompt,
+          uncond_prompt=negative_prompt if do_classifier_free_guidance else None,
+          max_embeddings_multiples=max_embeddings_multiples,
+          clip_skip=self.clip_skip,
+          **kwargs,
+      )
 
     if negative_scale is not None:
       _, real_uncond_embeddings, _ = get_weighted_text_embeddings(
@@ -742,11 +759,30 @@ class PipelineLike():
           **kwargs,
       )
 
-    if do_classifier_free_guidance:
-      if negative_scale is None:
-        text_embeddings = torch.cat([uncond_embeddings, text_embeddings])
-      else:
-        text_embeddings = torch.cat([uncond_embeddings, text_embeddings, real_uncond_embeddings])
+    if args.XTI_embeddings:
+      text_embeddings_concat = []
+      for layer in ['IN01', 'IN02', 'IN04', 'IN05', 'IN07', 'IN08', 'MID', 'OUT03', 'OUT04', 'OUT05', 'OUT06', 'OUT07', 'OUT08', 'OUT09', 'OUT10', 'OUT11']:
+        text_embeddings, uncond_embeddings, prompt_tokens = get_weighted_text_embeddings(
+          pipe=self,
+          prompt=prompt,
+          uncond_prompt=negative_prompt if do_classifier_free_guidance else None,
+          max_embeddings_multiples=max_embeddings_multiples,
+          clip_skip=self.clip_skip,
+          layer=layer,
+          **kwargs,
+        )
+        if do_classifier_free_guidance:
+          if negative_scale is None:
+            text_embeddings_concat.append(torch.cat([uncond_embeddings, text_embeddings]))
+          else:
+            text_embeddings_concat.append(torch.cat([uncond_embeddings, text_embeddings, real_uncond_embeddings]))
+      text_embeddings = torch.stack(text_embeddings_concat)
+    else:
+      if do_classifier_free_guidance:
+        if negative_scale is None:
+          text_embeddings = torch.cat([uncond_embeddings, text_embeddings])
+        else:
+          text_embeddings = torch.cat([uncond_embeddings, text_embeddings, real_uncond_embeddings])
 
     # CLIP guidanceで使用するembeddingsを取得する
     if self.clip_guidance_scale > 0:
@@ -1562,7 +1598,7 @@ def parse_prompt_attention(text):
   return res
 
 
-def get_prompts_with_weights(pipe: PipelineLike, prompt: List[str], max_length: int):
+def get_prompts_with_weights(pipe: PipelineLike, prompt: List[str], max_length: int, layer=None):
   r"""
   Tokenize a list of prompts and return its tokens with weights of each token.
   No padding, starting or ending token is included.
@@ -1578,7 +1614,7 @@ def get_prompts_with_weights(pipe: PipelineLike, prompt: List[str], max_length:
       # tokenize and discard the starting and the ending token
       token = pipe.tokenizer(word).input_ids[1:-1]
 
-      token = pipe.replace_token(token)
+      token = pipe.replace_token(token, layer=layer)
 
       text_token += token
       # copy the weight by length of token
@@ -1694,6 +1730,7 @@ def get_weighted_text_embeddings(
     skip_parsing: Optional[bool] = False,
     skip_weighting: Optional[bool] = False,
     clip_skip=None,
+    layer=None,
     **kwargs,
 ):
   r"""
@@ -1724,11 +1761,11 @@ def get_weighted_text_embeddings(
     prompt = [prompt]
 
   if not skip_parsing:
-    prompt_tokens, prompt_weights = get_prompts_with_weights(pipe, prompt, max_length - 2)
+    prompt_tokens, prompt_weights = get_prompts_with_weights(pipe, prompt, max_length - 2, layer=layer)
     if uncond_prompt is not None:
       if isinstance(uncond_prompt, str):
         uncond_prompt = [uncond_prompt]
-      uncond_tokens, uncond_weights = get_prompts_with_weights(pipe, uncond_prompt, max_length - 2)
+      uncond_tokens, uncond_weights = get_prompts_with_weights(pipe, uncond_prompt, max_length - 2, layer=layer)
   else:
     prompt_tokens = [
         token[1:-1] for token in pipe.tokenizer(prompt, max_length=max_length, truncation=True).input_ids
@@ -1961,6 +1998,9 @@ def main(args):
   # xformers、Hypernetwork対応
   if not args.diffusers_xformers:
     replace_unet_modules(unet, not args.xformers, args.xformers)
+  diffusers.models.UNet2DConditionModel.forward = unet_forward_XTI
+  diffusers.models.unet_2d_blocks.CrossAttnDownBlock2D.forward = downblock_forward_XTI
+  diffusers.models.unet_2d_blocks.CrossAttnUpBlock2D.forward = upblock_forward_XTI
 
   # tokenizerを読み込む
   print("loading tokenizer")
@@ -2196,6 +2236,50 @@ def main(args):
       for token_id, embed in zip(token_ids, embeds):
         token_embeds[token_id] = embed
 
+  if args.XTI_embeddings:
+    XTI_layers = ['IN01', 'IN02', 'IN04', 'IN05', 'IN07', 'IN08', 'MID', 'OUT03', 'OUT04', 'OUT05', 'OUT06', 'OUT07', 'OUT08', 'OUT09', 'OUT10', 'OUT11']
+    token_ids_embeds_XTI = []
+    for embeds_file in args.XTI_embeddings:
+      if model_util.is_safetensors(embeds_file):
+        from safetensors.torch import load_file
+        data = load_file(embeds_file)
+      else:
+        data = torch.load(embeds_file, map_location="cpu")
+      if set(data.keys()) != set(XTI_layers):
+        raise ValueError("NOT XTI")
+      embeds = torch.concat(list(data.values()))
+      num_vectors_per_token = data['MID'].size()[0]
+
+      token_string = os.path.splitext(os.path.basename(embeds_file))[0]
+      token_strings = [token_string] + [f"{token_string}{i+1}" for i in range(num_vectors_per_token - 1)]
+            
+      # add new word to tokenizer, count is num_vectors_per_token
+      num_added_tokens = tokenizer.add_tokens(token_strings)
+      assert num_added_tokens == num_vectors_per_token, f"tokenizer has same word to token string (filename). please rename the file / 指定した名前（ファイル名）のトークンが既に存在します。ファイルをリネームしてください: {embeds_file}"
+
+      token_ids = tokenizer.convert_tokens_to_ids(token_strings)
+      print(f"Textual Inversion embeddings `{token_string}` loaded. Tokens are added: {token_ids}")
+
+      #if num_vectors_per_token > 1:
+      pipe.add_token_replacement(token_ids[0], token_ids)
+            
+      token_strings_XTI = []
+      for layer_name in XTI_layers:
+        token_strings_XTI += [f"{t}_{layer_name}" for t in token_strings]
+      tokenizer.add_tokens(token_strings_XTI)
+      token_ids_XTI = tokenizer.convert_tokens_to_ids(token_strings_XTI)
+      token_ids_embeds_XTI.append((token_ids_XTI, embeds))
+      for t in token_ids:
+        t_XTI_dic = {}
+        for i, layer_name in enumerate(XTI_layers):
+          t_XTI_dic[layer_name] = t + (i + 1) * num_added_tokens
+        pipe.add_token_replacement_XTI(t, t_XTI_dic)
+        
+      text_encoder.resize_token_embeddings(len(tokenizer))
+      token_embeds = text_encoder.get_input_embeddings().weight.data
+      for token_ids, embeds in token_ids_embeds_XTI:
+        for token_id, embed in zip(token_ids, embeds):
+          token_embeds[token_id] = embed
   # promptを取得する
   if args.from_file is not None:
     print(f"reading prompts from {args.from_file}")
@@ -2754,6 +2838,8 @@ def setup_parser() -> argparse.ArgumentParser:
                       help='show metadata of network model / ネットワークモデルのメタデータを表示する')
   parser.add_argument("--textual_inversion_embeddings", type=str, default=None, nargs='*',
                       help='Embeddings files of Textual Inversion / Textual Inversionのembeddings')
+  parser.add_argument("--XTI_embeddings", type=str, default=None, nargs='*',
+                      help='Embeddings files of Extended Textual Inversion / Extended Textual Inversionのembeddings')
   parser.add_argument("--clip_skip", type=int, default=None, help='layer number from bottom to use in CLIP / CLIPの後ろからn層目の出力を使う')
   parser.add_argument("--max_embeddings_multiples", type=int, default=None,
                       help='max embeding multiples, max token length is 75 * multiples / トークン長をデフォルトの何倍とするか 75*この値 がトークン長となる')

library/train_util.py

@@ -391,6 +391,8 @@ class BaseDataset(torch.utils.data.Dataset):
 
         self.token_padding_disabled = False
         self.tag_frequency = {}
+        self.XTI_layers = None
+        self.token_strings = None
 
         self.enable_bucket = False
         self.bucket_manager: BucketManager = None  # not initialized
@@ -437,6 +439,10 @@ class BaseDataset(torch.utils.data.Dataset):
     def disable_token_padding(self):
         self.token_padding_disabled = True
 
+    def enable_XTI(self, layers=None, token_strings=None):
+        self.XTI_layers = layers
+        self.token_strings = token_strings
+
     def add_replacement(self, str_from, str_to):
         self.replacements[str_from] = str_to
 
@@ -870,9 +876,22 @@ class BaseDataset(torch.utils.data.Dataset):
             latents_list.append(latents)
 
             caption = self.process_caption(subset, image_info.caption)
-            captions.append(caption)
+            if self.XTI_layers:
+                caption_layer = []
+                for layer in self.XTI_layers:
+                    token_strings_from = " ".join(self.token_strings)
+                    token_strings_to = " ".join([f"{x}_{layer}" for x in self.token_strings])
+                    caption_ = caption.replace(token_strings_from, token_strings_to)
+                    caption_layer.append(caption_)
+                captions.append(caption_layer)
+            else:
+                captions.append(caption)
             if not self.token_padding_disabled:  # this option might be omitted in future
-                input_ids_list.append(self.get_input_ids(caption))
+                if self.XTI_layers:
+                    token_caption = self.get_input_ids(caption_layer)
+                else:
+                    token_caption = self.get_input_ids(caption)
+                input_ids_list.append(token_caption)
 
         example = {}
         example["loss_weights"] = torch.FloatTensor(loss_weights)
@@ -1273,6 +1292,10 @@ class DatasetGroup(torch.utils.data.ConcatDataset):
     #   for dataset in self.datasets:
     #     dataset.make_buckets()
 
+    def enable_XTI(self, *args, **kwargs):
+        for dataset in self.datasets:
+            dataset.enable_XTI(*args, **kwargs)
+
     def cache_latents(self, vae, vae_batch_size=1):
         for i, dataset in enumerate(self.datasets):
             print(f"[Dataset {i}]")

train_textual_inversion_XTI.py

@@ -0,0 +1,586 @@
+import importlib
+import argparse
+import gc
+import math
+import os
+import toml
+
+from tqdm import tqdm
+import torch
+from accelerate.utils import set_seed
+import diffusers
+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,
+)
+
+from XTI_hijack import unet_forward_XTI, downblock_forward_XTI, upblock_forward_XTI
+
+imagenet_templates_small = [
+    "a photo of a {}",
+    "a rendering of a {}",
+    "a cropped photo of the {}",
+    "the photo of a {}",
+    "a photo of a clean {}",
+    "a photo of a dirty {}",
+    "a dark photo of the {}",
+    "a photo of my {}",
+    "a photo of the cool {}",
+    "a close-up photo of a {}",
+    "a bright photo of the {}",
+    "a cropped photo of a {}",
+    "a photo of the {}",
+    "a good photo of the {}",
+    "a photo of one {}",
+    "a close-up photo of the {}",
+    "a rendition of the {}",
+    "a photo of the clean {}",
+    "a rendition of a {}",
+    "a photo of a nice {}",
+    "a good photo of a {}",
+    "a photo of the nice {}",
+    "a photo of the small {}",
+    "a photo of the weird {}",
+    "a photo of the large {}",
+    "a photo of a cool {}",
+    "a photo of a small {}",
+]
+
+imagenet_style_templates_small = [
+    "a painting in the style of {}",
+    "a rendering in the style of {}",
+    "a cropped painting in the style of {}",
+    "the painting in the style of {}",
+    "a clean painting in the style of {}",
+    "a dirty painting in the style of {}",
+    "a dark painting in the style of {}",
+    "a picture in the style of {}",
+    "a cool painting in the style of {}",
+    "a close-up painting in the style of {}",
+    "a bright painting in the style of {}",
+    "a cropped painting in the style of {}",
+    "a good painting in the style of {}",
+    "a close-up painting in the style of {}",
+    "a rendition in the style of {}",
+    "a nice painting in the style of {}",
+    "a small painting in the style of {}",
+    "a weird painting in the style of {}",
+    "a large painting in the style of {}",
+]
+
+
+def collate_fn(examples):
+    return examples[0]
+
+
+def train(args):
+    if args.output_name is None:
+        args.output_name = args.token_string
+    use_template = args.use_object_template or args.use_style_template
+
+    train_util.verify_training_args(args)
+    train_util.prepare_dataset_args(args, True)
+
+    cache_latents = args.cache_latents
+
+    if args.seed is not None:
+        set_seed(args.seed)
+
+    tokenizer = train_util.load_tokenizer(args)
+
+    # acceleratorを準備する
+    print("prepare accelerator")
+    accelerator, unwrap_model = 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)
+
+    # モデルを読み込む
+    text_encoder, vae, unet, _ = train_util.load_target_model(args, weight_dtype)
+
+    # Convert the init_word to token_id
+    if args.init_word is not None:
+        init_token_ids = tokenizer.encode(args.init_word, add_special_tokens=False)
+        if len(init_token_ids) > 1 and len(init_token_ids) != args.num_vectors_per_token:
+            print(
+                f"token length for init words is not same to num_vectors_per_token, init words is repeated or truncated / 初期化単語のトークン長がnum_vectors_per_tokenと合わないため、繰り返しまたは切り捨てが発生します: length {len(init_token_ids)}"
+            )
+    else:
+        init_token_ids = None
+
+    # add new word to tokenizer, count is num_vectors_per_token
+    token_strings = [args.token_string] + [f"{args.token_string}{i+1}" for i in range(args.num_vectors_per_token - 1)]
+    num_added_tokens = tokenizer.add_tokens(token_strings)
+    assert (
+        num_added_tokens == args.num_vectors_per_token
+    ), f"tokenizer has same word to token string. please use another one / 指定したargs.token_stringは既に存在します。別の単語を使ってください: {args.token_string}"
+
+    token_ids = tokenizer.convert_tokens_to_ids(token_strings)
+    print(f"tokens are added: {token_ids}")
+    assert min(token_ids) == token_ids[0] and token_ids[-1] == token_ids[0] + len(token_ids) - 1, f"token ids is not ordered"
+    assert len(tokenizer) - 1 == token_ids[-1], f"token ids is not end of tokenize: {len(tokenizer)}"
+
+    token_strings_XTI = []
+    XTI_layers = ['IN01', 'IN02', 'IN04', 'IN05', 'IN07', 'IN08', 'MID', 'OUT03', 'OUT04', 'OUT05', 'OUT06', 'OUT07', 'OUT08', 'OUT09', 'OUT10', 'OUT11']
+    for layer_name in XTI_layers:
+        token_strings_XTI += [f"{t}_{layer_name}" for t in token_strings]
+
+    tokenizer.add_tokens(token_strings_XTI)
+    token_ids_XTI = tokenizer.convert_tokens_to_ids(token_strings_XTI)
+    print(f"tokens are added (XTI): {token_ids_XTI}")
+    # Resize the token embeddings as we are adding new special tokens to the tokenizer
+    text_encoder.resize_token_embeddings(len(tokenizer))
+
+    # Initialise the newly added placeholder token with the embeddings of the initializer token
+    token_embeds = text_encoder.get_input_embeddings().weight.data
+    if init_token_ids is not None:
+        for i, token_id in enumerate(token_ids_XTI):
+            token_embeds[token_id] = token_embeds[init_token_ids[(i // 16) % len(init_token_ids)]]
+            # print(token_id, token_embeds[token_id].mean(), token_embeds[token_id].min())
+
+    # load weights
+    if args.weights is not None:
+        embeddings = load_weights(args.weights)
+        assert len(token_ids) == len(
+            embeddings
+        ), f"num_vectors_per_token is mismatch for weights / 指定した重みとnum_vectors_per_tokenの値が異なります: {len(embeddings)}"
+        # print(token_ids, embeddings.size())
+        for token_id, embedding in zip(token_ids_XTI, embeddings):
+            token_embeds[token_id] = embedding
+            # print(token_id, token_embeds[token_id].mean(), token_embeds[token_id].min())
+        print(f"weighs loaded")
+
+    print(f"create embeddings for {args.num_vectors_per_token} tokens, for {args.token_string}")
+
+    # データセットを準備する
+    blueprint_generator = BlueprintGenerator(ConfigSanitizer(True, True, False))
+    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", "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:
+        use_dreambooth_method = args.in_json is None
+        if use_dreambooth_method:
+            print("Use DreamBooth method.")
+            user_config = {
+                "datasets": [
+                    {"subsets": config_util.generate_dreambooth_subsets_config_by_subdirs(args.train_data_dir, args.reg_data_dir)}
+                ]
+            }
+        else:
+            print("Train 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=tokenizer)
+    train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
+    train_dataset_group.enable_XTI(XTI_layers, token_strings=token_strings)
+
+    # make captions: tokenstring tokenstring1 tokenstring2 ...tokenstringn という文字列に書き換える超乱暴な実装
+    if use_template:
+        print("use template for training captions. is object: {args.use_object_template}")
+        templates = imagenet_templates_small if args.use_object_template else imagenet_style_templates_small
+        replace_to = " ".join(token_strings)
+        captions = []
+        for tmpl in templates:
+            captions.append(tmpl.format(replace_to))
+        train_dataset_group.add_replacement("", captions)
+
+        if args.num_vectors_per_token > 1:
+            prompt_replacement = [args.token_string, replace_to]
+        else:
+            prompt_replacement = None
+    else:
+        if args.num_vectors_per_token > 1:
+            replace_to = " ".join(token_strings)
+            train_dataset_group.add_replacement(args.token_string, replace_to)
+            prompt_replacement = [args.token_string, replace_to]
+        else:
+            prompt_replacement = None
+
+    if args.debug_dataset:
+        train_util.debug_dataset(train_dataset_group, show_input_ids=True)
+        return
+    if len(train_dataset_group) == 0:
+        print("No data found. Please verify arguments / 画像がありません。引数指定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"
+
+    # 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)
+    diffusers.models.UNet2DConditionModel.forward = unet_forward_XTI
+    diffusers.models.unet_2d_blocks.CrossAttnDownBlock2D.forward = downblock_forward_XTI
+    diffusers.models.unet_2d_blocks.CrossAttnUpBlock2D.forward = upblock_forward_XTI
+
+    # 学習を準備する
+    if cache_latents:
+        vae.to(accelerator.device, dtype=weight_dtype)
+        vae.requires_grad_(False)
+        vae.eval()
+        with torch.no_grad():
+            train_dataset_group.cache_latents(vae, args.vae_batch_size)
+        vae.to("cpu")
+        if torch.cuda.is_available():
+            torch.cuda.empty_cache()
+        gc.collect()
+
+    if args.gradient_checkpointing:
+        unet.enable_gradient_checkpointing()
+        text_encoder.gradient_checkpointing_enable()
+
+    # 学習に必要なクラスを準備する
+    print("prepare optimizer, data loader etc.")
+    trainable_params = text_encoder.get_input_embeddings().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=collate_fn,
+        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 * len(train_dataloader)
+        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}")
+
+    # lr schedulerを用意する
+    lr_scheduler = train_util.get_scheduler_fix(args, optimizer, accelerator.num_processes)
+
+    # acceleratorがなんかよろしくやってくれるらしい
+    text_encoder, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
+        text_encoder, optimizer, train_dataloader, lr_scheduler
+    )
+
+    index_no_updates = torch.arange(len(tokenizer)) < token_ids_XTI[0]
+    # print(len(index_no_updates), torch.sum(index_no_updates))
+    orig_embeds_params = unwrap_model(text_encoder).get_input_embeddings().weight.data.detach().clone()
+
+    # Freeze all parameters except for the token embeddings in text encoder
+    text_encoder.requires_grad_(True)
+    text_encoder.text_model.encoder.requires_grad_(False)
+    text_encoder.text_model.final_layer_norm.requires_grad_(False)
+    text_encoder.text_model.embeddings.position_embedding.requires_grad_(False)
+    # text_encoder.text_model.embeddings.token_embedding.requires_grad_(True)
+
+    unet.requires_grad_(False)
+    unet.to(accelerator.device, dtype=weight_dtype)
+    if args.gradient_checkpointing:  # according to TI example in Diffusers, train is required
+        unet.train()
+    else:
+        unet.eval()
+
+    if not cache_latents:
+        vae.requires_grad_(False)
+        vae.eval()
+        vae.to(accelerator.device, dtype=weight_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)
+        text_encoder.to(weight_dtype)
+
+    # resumeする
+    if args.resume is not None:
+        print(f"resume training from state: {args.resume}")
+        accelerator.load_state(args.resume)
+
+    # 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
+    print("running training / 学習開始")
+    print(f"  num train images * repeats / 学習画像の数×繰り返し回数: {train_dataset_group.num_train_images}")
+    print(f"  num reg images / 正則化画像の数: {train_dataset_group.num_reg_images}")
+    print(f"  num batches per epoch / 1epochのバッチ数: {len(train_dataloader)}")
+    print(f"  num epochs / epoch数: {num_train_epochs}")
+    print(f"  batch size per device / バッチサイズ: {args.train_batch_size}")
+    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}")
+    print(f"  gradient ccumulation steps / 勾配を合計するステップ数 = {args.gradient_accumulation_steps}")
+    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
+    )
+
+    if accelerator.is_main_process:
+        accelerator.init_trackers("textual_inversion")
+
+    for epoch in range(num_train_epochs):
+        print(f"epoch {epoch+1}/{num_train_epochs}")
+        train_dataset_group.set_current_epoch(epoch + 1)
+
+        text_encoder.train()
+
+        loss_total = 0
+        for step, batch in enumerate(train_dataloader):
+            with accelerator.accumulate(text_encoder):
+                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=weight_dtype)).latent_dist.sample()
+                    latents = latents * 0.18215
+                b_size = latents.shape[0]
+
+                # Get the text embedding for conditioning
+                input_ids = batch["input_ids"].to(accelerator.device)
+                # weight_dtype) use float instead of fp16/bf16 because text encoder is float
+                encoder_hidden_states = torch.stack([train_util.get_hidden_states(args, s, tokenizer, text_encoder, weight_dtype) for s in torch.split(input_ids, 1, dim=1)])
+
+                # Sample noise that we'll add to the latents
+                noise = torch.randn_like(latents, device=latents.device)
+                if args.noise_offset:
+                    # https://www.crosslabs.org//blog/diffusion-with-offset-noise
+                    noise += args.noise_offset * torch.randn((latents.shape[0], latents.shape[1], 1, 1), device=latents.device)
+
+                # Sample a random timestep for each image
+                timesteps = torch.randint(0, noise_scheduler.config.num_train_timesteps, (b_size,), device=latents.device)
+                timesteps = timesteps.long()
+
+                # Add noise to the latents according to the noise magnitude at each timestep
+                # (this is the forward diffusion process)
+                noisy_latents = noise_scheduler.add_noise(latents, noise, timesteps)
+
+                # Predict the noise residual
+                noise_pred = unet(noisy_latents, timesteps, encoder_hidden_states=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
+
+                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 = text_encoder.get_input_embeddings().parameters()
+                    accelerator.clip_grad_norm_(params_to_clip, args.max_grad_norm)
+
+                optimizer.step()
+                lr_scheduler.step()
+                optimizer.zero_grad(set_to_none=True)
+
+                # Let's make sure we don't update any embedding weights besides the newly added token
+                with torch.no_grad():
+                    unwrap_model(text_encoder).get_input_embeddings().weight[index_no_updates] = orig_embeds_params[
+                        index_no_updates
+                    ]
+
+            # 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, prompt_replacement
+                )
+
+            current_loss = loss.detach().item()
+            if args.logging_dir is not None:
+                logs = {"loss": current_loss, "lr": float(lr_scheduler.get_last_lr()[0])}
+                if args.optimizer_type.lower() == "DAdaptation".lower():  # tracking d*lr value
+                    logs["lr/d*lr"] = (
+                        lr_scheduler.optimizers[0].param_groups[0]["d"] * lr_scheduler.optimizers[0].param_groups[0]["lr"]
+                    )
+                accelerator.log(logs, step=global_step)
+
+            loss_total += current_loss
+            avr_loss = loss_total / (step + 1)
+            logs = {"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_total / len(train_dataloader)}
+            accelerator.log(logs, step=epoch + 1)
+
+        accelerator.wait_for_everyone()
+
+        updated_embs = unwrap_model(text_encoder).get_input_embeddings().weight[token_ids_XTI].data.detach().clone()
+
+        if args.save_every_n_epochs is not None:
+            model_name = train_util.DEFAULT_EPOCH_NAME if args.output_name is None else args.output_name
+
+            def save_func():
+                ckpt_name = train_util.EPOCH_FILE_NAME.format(model_name, epoch + 1) + "." + args.save_model_as
+                ckpt_file = os.path.join(args.output_dir, ckpt_name)
+                print(f"saving checkpoint: {ckpt_file}")
+                save_weights(ckpt_file, updated_embs, save_dtype)
+
+            def remove_old_func(old_epoch_no):
+                old_ckpt_name = train_util.EPOCH_FILE_NAME.format(model_name, old_epoch_no) + "." + args.save_model_as
+                old_ckpt_file = os.path.join(args.output_dir, old_ckpt_name)
+                if os.path.exists(old_ckpt_file):
+                    print(f"removing old checkpoint: {old_ckpt_file}")
+                    os.remove(old_ckpt_file)
+
+            saving = train_util.save_on_epoch_end(args, save_func, remove_old_func, epoch + 1, num_train_epochs)
+            if saving and args.save_state:
+                train_util.save_state_on_epoch_end(args, accelerator, model_name, epoch + 1)
+
+        train_util.sample_images(
+            accelerator, args, epoch + 1, global_step, accelerator.device, vae, tokenizer, text_encoder, unet, prompt_replacement
+        )
+
+        # end of epoch
+
+    is_main_process = accelerator.is_main_process
+    if is_main_process:
+        text_encoder = unwrap_model(text_encoder)
+
+    accelerator.end_training()
+
+    if args.save_state:
+        train_util.save_state_on_train_end(args, accelerator)
+
+    updated_embs = text_encoder.get_input_embeddings().weight[token_ids_XTI].data.detach().clone()
+
+    del accelerator  # この後メモリを使うのでこれは消す
+
+    if is_main_process:
+        os.makedirs(args.output_dir, exist_ok=True)
+
+        model_name = train_util.DEFAULT_LAST_OUTPUT_NAME if args.output_name is None else args.output_name
+        ckpt_name = model_name + "." + args.save_model_as
+        ckpt_file = os.path.join(args.output_dir, ckpt_name)
+
+        print(f"save trained model to {ckpt_file}")
+        save_weights(ckpt_file, updated_embs, save_dtype)
+        print("model saved.")
+
+
+def save_weights(file, updated_embs, save_dtype):
+    updated_embs = updated_embs.reshape(16, -1, updated_embs.shape[-1])
+    updated_embs = updated_embs.chunk(16)
+    XTI_layers = ['IN01', 'IN02', 'IN04', 'IN05', 'IN07', 'IN08', 'MID', 'OUT03', 'OUT04', 'OUT05', 'OUT06', 'OUT07', 'OUT08', 'OUT09', 'OUT10', 'OUT11']
+    state_dict = {}
+    for i, layer_name in enumerate(XTI_layers):
+        state_dict[layer_name] = updated_embs[i].squeeze(0).detach().clone().to("cpu").to(save_dtype)
+
+    # if save_dtype is not None:
+    #     for key in list(state_dict.keys()):
+    #         v = state_dict[key]
+    #         v = v.detach().clone().to("cpu").to(save_dtype)
+    #         state_dict[key] = v
+
+    if os.path.splitext(file)[1] == ".safetensors":
+        from safetensors.torch import save_file
+
+        save_file(state_dict, file)
+    else:
+        torch.save(state_dict, file)  # can be loaded in Web UI
+
+
+def load_weights(file):
+    if os.path.splitext(file)[1] == ".safetensors":
+        from safetensors.torch import load_file
+
+        data = load_file(file)
+    else:
+        raise ValueError(f"NOT XTI: {file}")
+
+    if len(data.values()) != 16:
+        raise ValueError(f"NOT XTI: {file}")
+    
+    emb = torch.concat([x for x in data.values()])
+
+    return emb
+
+
+def setup_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser()
+
+    train_util.add_sd_models_arguments(parser)
+    train_util.add_dataset_arguments(parser, True, True, False)
+    train_util.add_training_arguments(parser, True)
+    train_util.add_optimizer_arguments(parser)
+    config_util.add_config_arguments(parser)
+
+    parser.add_argument(
+        "--save_model_as",
+        type=str,
+        default="pt",
+        choices=[None, "ckpt", "pt", "safetensors"],
+        help="format to save the model (default is .pt) / モデル保存時の形式（デフォルトはpt）",
+    )
+
+    parser.add_argument("--weights", type=str, default=None, help="embedding weights to initialize / 学習するネットワークの初期重み")
+    parser.add_argument(
+        "--num_vectors_per_token", type=int, default=1, help="number of vectors per token / トークンに割り当てるembeddingsの要素数"
+    )
+    parser.add_argument(
+        "--token_string",
+        type=str,
+        default=None,
+        help="token string used in training, must not exist in tokenizer / 学習時に使用されるトークン文字列、tokenizerに存在しない文字であること",
+    )
+    parser.add_argument("--init_word", type=str, default=None, help="words to initialize vector / ベクトルを初期化に使用する単語、複数可")
+    parser.add_argument(
+        "--use_object_template",
+        action="store_true",
+        help="ignore caption and use default templates for object / キャプションは使わずデフォルトの物体用テンプレートで学習する",
+    )
+    parser.add_argument(
+        "--use_style_template",
+        action="store_true",
+        help="ignore caption and use default templates for stype / キャプションは使わずデフォルトのスタイル用テンプレートで学習する",
+    )
+
+    return parser
+
+
+if __name__ == "__main__":
+    parser = setup_parser()
+
+    args = parser.parse_args()
+    args = train_util.read_config_from_file(args, parser)
+
+    train(args)