Merge pull request #16 from kohya-ss/dev

Add LoRA training/generating.

gen_img_diffusers.py

@@ -1,7 +1,7 @@
 # txt2img with Diffusers: supports SD checkpoints, EulerScheduler, clip-skip, 225 tokens, Hypernetwork etc...
 
 # v2: CLIP guided Stable Diffusion, Image guided Stable Diffusion, highres. fix
-# v3: Add dpmsolver/dpmsolver++, add VAE loading, add upscale, add 'bf16', fix the issue hypernetwork_mul is not working
+# v3: Add dpmsolver/dpmsolver++, add VAE loading, add upscale, add 'bf16', fix the issue network_mul is not working
 # v4: SD2.0 support (new U-Net/text encoder/tokenizer), simplify by DiffUsers 0.9.0, no_preview in interactive mode
 # v5: fix clip_sample=True for scheduler, add VGG guidance
 # v6: refactor to use model util, load VAE without vae folder, support safe tensors
@@ -333,7 +333,7 @@ def replace_unet_modules(unet: diffusers.models.unet_2d_condition.UNet2DConditio
 
 
 def replace_unet_cross_attn_to_memory_efficient():
-  print("Replace CrossAttention.forward to use Hypernetwork and FlashAttention")
+  print("Replace CrossAttention.forward to use NAI style Hypernetwork and FlashAttention")
   flash_func = FlashAttentionFunction
 
   def forward_flash_attn(self, x, context=None, mask=None):
@@ -373,7 +373,7 @@ def replace_unet_cross_attn_to_memory_efficient():
 
 
 def replace_unet_cross_attn_to_xformers():
-  print("Replace CrossAttention.forward to use Hypernetwork and xformers")
+  print("Replace CrossAttention.forward to use NAI style Hypernetwork and xformers")
   try:
     import xformers.ops
   except ImportError:
@@ -1867,25 +1867,6 @@ def main(args):
   if not args.diffusers_xformers:
     replace_unet_modules(unet, not args.xformers, args.xformers)
 
-  # hypernetworkを組み込む
-  if args.hypernetwork_module is not None:
-    assert not args.diffusers_xformers, "cannot use hypernetwork with diffusers_xformers / diffusers_xformers指定時はHypernetworkは利用できません"
-
-    print("import hypernetwork module:", args.hypernetwork_module)
-    hyp_module = importlib.import_module(args.hypernetwork_module)
-
-    hypernetwork = hyp_module.Hypernetwork(args.hypernetwork_mul)
-
-    print("load hypernetwork weights from:", args.hypernetwork_weights)
-    hyp_sd = torch.load(args.hypernetwork_weights, map_location='cpu')
-    success = hypernetwork.load_from_state_dict(hyp_sd)
-    assert success, "hypernetwork weights loading failed."
-
-    if args.opt_channels_last:
-      hypernetwork.to(memory_format=torch.channels_last)
-  else:
-    hypernetwork = None
-
   # tokenizerを読み込む
   print("loading tokenizer")
   if use_stable_diffusion_format:
@@ -2000,10 +1981,27 @@ def main(args):
   if vgg16_model is not None:
     vgg16_model.to(dtype).to(device)
 
-  if hypernetwork is not None:
-    hypernetwork.to(dtype).to(device)
-    print("apply hypernetwork")
-    hypernetwork.apply_to_diffusers(vae, text_encoder, unet)
+  # networkを組み込む
+  if args.network_module is not None:
+    # assert not args.diffusers_xformers, "cannot use network with diffusers_xformers / diffusers_xformers指定時はnetworkは利用できません"
+
+    print("import network module:", args.network_module)
+    network_module = importlib.import_module(args.network_module)
+
+    network = network_module.create_network(args.network_mul, args.network_dim, vae,text_encoder, unet) # , **net_kwargs)
+    if network is None:
+      return
+
+    print("load network weights from:", args.network_weights)
+    network.load_weights(args.network_weights)
+
+    network.apply_to(text_encoder, unet)
+
+    if args.opt_channels_last:
+      network.to(memory_format=torch.channels_last)
+    network.to(dtype).to(device)
+  else:
+    network = None
 
   if args.opt_channels_last:
     print(f"set optimizing: channels last")
@@ -2012,8 +2010,8 @@ def main(args):
     unet.to(memory_format=torch.channels_last)
     if clip_model is not None:
       clip_model.to(memory_format=torch.channels_last)
-    if hypernetwork is not None:
-      hypernetwork.to(memory_format=torch.channels_last)
+    if network is not None:
+      network.to(memory_format=torch.channels_last)
     if vgg16_model is not None:
       vgg16_model.to(memory_format=torch.channels_last)
 
@@ -2491,9 +2489,11 @@ if __name__ == '__main__':
                       help='use xformers by diffusers (Hypernetworks doen\'t work) / Diffusersでxformersを使用する（Hypernetwork利用不可）')
   parser.add_argument("--opt_channels_last", action='store_true',
                       help='set channels last option to model / モデルにchannles lastを指定し最適化する')
-  parser.add_argument("--hypernetwork_module", type=str, default=None, help='Hypernetwork module to use / Hypernetworkを使う時そのモジュール名')
-  parser.add_argument("--hypernetwork_weights", type=str, default=None, help='Hypernetwork weights to load / Hypernetworkの重み')
-  parser.add_argument("--hypernetwork_mul", type=float, default=1.0, help='Hypernetwork multiplier / Hypernetworkの効果の倍率')
+  parser.add_argument("--network_module", type=str, default=None, help='Hypernetwork module to use / Hypernetworkを使う時そのモジュール名')
+  parser.add_argument("--network_weights", type=str, default=None, help='Hypernetwork weights to load / Hypernetworkの重み')
+  parser.add_argument("--network_mul", type=float, default=1.0, help='Hypernetwork multiplier / Hypernetworkの効果の倍率')
+  parser.add_argument("--network_dim", type=int, default=None,
+                      help='network dimensions (depends on each network) / モジュールの次元数（ネットワークにより定義は異なります）')
   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')

networks/lora.py

@@ -0,0 +1,190 @@
+# LoRA network module
+# reference:
+# https://github.com/microsoft/LoRA/blob/main/loralib/layers.py
+# https://github.com/cloneofsimo/lora/blob/master/lora_diffusion/lora.py
+
+import math
+import os
+import torch
+
+
+class LoRAModule(torch.nn.Module):
+  """
+  replaces forward method of the original Linear, instead of replacing the original Linear module.
+  """
+
+  def __init__(self, lora_name, org_module: torch.nn.Module, multiplier=1.0, lora_dim=4):
+    super().__init__()
+    self.lora_name = lora_name
+
+    if org_module.__class__.__name__ == 'Conv2d':
+      in_dim = org_module.in_channels
+      out_dim = org_module.out_channels
+      self.lora_down = torch.nn.Conv2d(in_dim, lora_dim, (1, 1), bias=False)
+      self.lora_up = torch.nn.Conv2d(lora_dim, out_dim, (1, 1), bias=False)
+    else:
+      in_dim = org_module.in_features
+      out_dim = org_module.out_features
+      self.lora_down = torch.nn.Linear(in_dim, lora_dim, bias=False)
+      self.lora_up = torch.nn.Linear(lora_dim, out_dim, bias=False)
+
+    # same as microsoft's
+    torch.nn.init.kaiming_uniform_(self.lora_down.weight, a=math.sqrt(5))
+    torch.nn.init.zeros_(self.lora_up.weight)
+
+    self.multiplier = multiplier
+    self.org_module = org_module                  # remove in applying
+
+  def apply_to(self):
+    self.org_forward = self.org_module.forward
+    self.org_module.forward = self.forward
+    del self.org_module
+
+  def forward(self, x):
+    return self.org_forward(x) + self.lora_up(self.lora_down(x)) * self.multiplier
+
+
+def create_network(multiplier, network_dim, vae, text_encoder, unet, **kwargs):
+  if network_dim is None:
+    network_dim = 4                     # default
+  network = LoRANetwork(text_encoder, unet, multiplier=multiplier, lora_dim=network_dim)
+  return network
+
+
+class LoRANetwork(torch.nn.Module):
+  UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel", "Attention"]
+  TEXT_ENCODER_TARGET_REPLACE_MODULE = ["CLIPAttention", "CLIPMLP"]
+  LORA_PREFIX_UNET = 'lora_unet'
+  LORA_PREFIX_TEXT_ENCODER = 'lora_te'
+
+  def __init__(self, text_encoder, unet, multiplier=1.0, lora_dim=4) -> None:
+    super().__init__()
+    self.multiplier = multiplier
+    self.lora_dim = lora_dim
+
+    # create module instances
+    def create_modules(prefix, root_module: torch.nn.Module, target_replace_modules) -> list[LoRAModule]:
+      loras = []
+      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():
+            if child_module.__class__.__name__ == "Linear" or (child_module.__class__.__name__ == "Conv2d" and child_module.kernel_size == (1, 1)):
+              lora_name = prefix + '.' + name + '.' + child_name
+              lora_name = lora_name.replace('.', '_')
+              lora = LoRAModule(lora_name, child_module, self.multiplier, self.lora_dim)
+              loras.append(lora)
+      return loras
+
+    self.text_encoder_loras = create_modules(LoRANetwork.LORA_PREFIX_TEXT_ENCODER,
+                                             text_encoder, LoRANetwork.TEXT_ENCODER_TARGET_REPLACE_MODULE)
+    print(f"create LoRA for Text Encoder: {len(self.text_encoder_loras)} modules.")
+
+    self.unet_loras = create_modules(LoRANetwork.LORA_PREFIX_UNET, unet, LoRANetwork.UNET_TARGET_REPLACE_MODULE)
+    print(f"create LoRA for U-Net: {len(self.unet_loras)} modules.")
+
+    self.weights_sd = None
+
+    # assertion
+    names = set()
+    for lora in self.text_encoder_loras + self.unet_loras:
+      assert lora.lora_name not in names, f"duplicated lora name: {lora.lora_name}"
+      names.add(lora.lora_name)
+
+  def load_weights(self, file):
+    if os.path.splitext(file)[1] == '.safetensors':
+      from safetensors.torch import load_file
+      self.weights_sd = load_file(file)
+    else:
+      self.weights_sd = torch.load(file, map_location='cpu')
+
+  def apply_to(self, text_encoder, unet, apply_text_encoder=None, apply_unet=None):
+    if self.weights_sd:
+      weights_has_text_encoder = weights_has_unet = False
+      for key in self.weights_sd.keys():
+        if key.startswith(LoRANetwork.LORA_PREFIX_TEXT_ENCODER):
+          weights_has_text_encoder = True
+        elif key.startswith(LoRANetwork.LORA_PREFIX_UNET):
+          weights_has_unet = True
+
+      if apply_text_encoder is None:
+        apply_text_encoder = weights_has_text_encoder
+      else:
+        assert apply_text_encoder == weights_has_text_encoder, f"text encoder weights: {weights_has_text_encoder} but text encoder flag: {apply_text_encoder} / 重みとText Encoderのフラグが矛盾しています"
+
+      if apply_unet is None:
+        apply_unet = weights_has_unet
+      else:
+        assert apply_unet == weights_has_unet, f"u-net weights: {weights_has_unet} but u-net flag: {apply_unet} / 重みとU-Netのフラグが矛盾しています"
+    else:
+      assert apply_text_encoder is not None and apply_unet is not None, f"internal error: flag not set"
+
+    if apply_text_encoder:
+      print("enable LoRA for text encoder")
+    else:
+      self.text_encoder_loras = []
+
+    if apply_unet:
+      print("enable LoRA for U-Net")
+    else:
+      self.unet_loras = []
+
+    for lora in self.text_encoder_loras + self.unet_loras:
+      lora.apply_to()
+      self.add_module(lora.lora_name, lora)
+
+    if self.weights_sd:
+      # if some weights are not in state dict, it is ok because initial LoRA does nothing (lora_up is initialized by zeros)
+      info = self.load_state_dict(self.weights_sd, False)
+      print(f"weights are loaded: {info}")
+
+  def enable_gradient_checkpointing(self):
+    # not supported
+    pass
+
+  def prepare_optimizer_params(self, text_encoder_lr, unet_lr):
+    def enumerate_params(loras):
+      params = []
+      for lora in loras:
+        params.extend(lora.parameters())
+      return params
+
+    self.requires_grad_(True)
+    params = []
+
+    if self.text_encoder_loras:
+      param_data = {'params': enumerate_params(self.text_encoder_loras)}
+      if text_encoder_lr is not None:
+        param_data['lr'] = text_encoder_lr
+      params.append(param_data)
+
+    if self.unet_loras:
+      param_data = {'params': enumerate_params(self.unet_loras)}
+      if unet_lr is not None:
+        param_data['lr'] = unet_lr
+      params.append(param_data)
+
+    return params
+
+  def prepare_grad_etc(self, text_encoder, unet):
+    self.requires_grad_(True)
+
+  def on_epoch_start(self, text_encoder, unet):
+    self.train()
+
+  def get_trainable_params(self):
+    return self.parameters()
+
+  def save_weights(self, file, dtype):
+    state_dict = self.state_dict()
+
+    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)
+    else:
+      torch.save(state_dict, file)

networks/merge_lora.py

@@ -0,0 +1,159 @@
+
+
+import argparse
+import os
+import torch
+from safetensors.torch import load_file, save_file
+import library.model_util as model_util
+import lora
+
+
+def load_state_dict(file_name, dtype):
+  if os.path.splitext(file_name)[1] == '.safetensors':
+    sd = load_file(file_name)
+  else:
+    sd = torch.load(file_name, map_location='cpu')
+  for key in list(sd.keys()):
+    if type(sd[key]) == torch.Tensor:
+      sd[key] = sd[key].to(dtype)
+  return sd
+
+
+def save_to_file(file_name, model, state_dict, dtype):
+  if dtype is not None:
+    for key in list(state_dict.keys()):
+      if type(state_dict[key]) == torch.Tensor:
+        state_dict[key] = state_dict[key].to(dtype)
+
+  if os.path.splitext(file_name)[1] == '.safetensors':
+    save_file(model, file_name)
+  else:
+    torch.save(model, file_name)
+
+
+def merge_to_sd_model(text_encoder, unet, models, ratios, merge_dtype):
+  text_encoder.to(merge_dtype)
+  unet.to(merge_dtype)
+
+  # create module map
+  name_to_module = {}
+  for i, root_module in enumerate([text_encoder, unet]):
+    if i == 0:
+      prefix = lora.LoRANetwork.LORA_PREFIX_TEXT_ENCODER
+      target_replace_modules = lora.LoRANetwork.TEXT_ENCODER_TARGET_REPLACE_MODULE
+    else:
+      prefix = lora.LoRANetwork.LORA_PREFIX_UNET
+      target_replace_modules = lora.LoRANetwork.UNET_TARGET_REPLACE_MODULE
+
+    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():
+          if child_module.__class__.__name__ == "Linear" or (child_module.__class__.__name__ == "Conv2d" and child_module.kernel_size == (1, 1)):
+            lora_name = prefix + '.' + name + '.' + child_name
+            lora_name = lora_name.replace('.', '_')
+            name_to_module[lora_name] = child_module
+
+  for model, ratio in zip(models, ratios):
+    print(f"loading: {model}")
+    lora_sd = load_state_dict(model, merge_dtype)
+
+    print(f"merging...")
+    for key in lora_sd.keys():
+      if "lora_down" in key:
+        up_key = key.replace("lora_down", "lora_up")
+
+        # find original module for this lora
+        module_name = '.'.join(key.split('.')[:-2])               # remove trailing ".lora_down.weight"
+        if module_name not in name_to_module:
+          print(f"no module found for LoRA weight: {key}")
+          continue
+        module = name_to_module[module_name]
+        # print(f"apply {key} to {module}")
+
+        down_weight = lora_sd[key]
+        up_weight = lora_sd[up_key]
+
+        # W <- W + U * D
+        weight = module.weight
+        if len(weight.size()) == 2:
+          # linear
+          weight = weight + ratio * (up_weight @ down_weight)
+        else:
+          # conv2d
+          weight = weight + ratio * (up_weight.squeeze(3).squeeze(2) @ down_weight.squeeze(3).squeeze(2)).unsqueeze(2).unsqueeze(3)
+
+        module.weight = torch.nn.Parameter(weight)
+
+
+def merge_lora_models(models, ratios, merge_dtype):
+  merged_sd = {}
+
+  for model, ratio in zip(models, ratios):
+    print(f"loading: {model}")
+    lora_sd = load_state_dict(model, merge_dtype)
+
+    print(f"merging...")
+    for key in lora_sd.keys():
+      if key in merged_sd:
+        assert merged_sd[key].size() == lora_sd[key].size(
+        ), f"weights shape mismatch merging v1 and v2, different dims? / 重みのサイズが合いません。v1とv2、または次元数の異なるモデルはマージできません"
+        merged_sd[key] = merged_sd[key] + lora_sd[key] * ratio
+      else:
+        merged_sd[key] = lora_sd[key] * ratio
+
+  return merged_sd
+
+
+def merge(args):
+  assert len(args.models) == len(args.ratios), f"number of models must be equal to number of ratios / モデルの数と重みの数は合わせてください"
+
+  def str_to_dtype(p):
+    if p == 'float':
+      return torch.float
+    if p == 'fp16':
+      return torch.float16
+    if p == 'bf16':
+      return torch.bfloat16
+    return None
+
+  merge_dtype = str_to_dtype(args.precision)
+  save_dtype = str_to_dtype(args.save_precision)
+  if save_dtype is None:
+    save_dtype = merge_dtype
+
+  if args.sd_model is not None:
+    print(f"loading SD model: {args.sd_model}")
+
+    text_encoder, vae, unet = model_util.load_models_from_stable_diffusion_checkpoint(args.v2, args.sd_model)
+
+    merge_to_sd_model(text_encoder, unet, args.models, args.ratios, merge_dtype)
+
+    print(f"saving SD model to: {args.save_to}")
+    model_util.save_stable_diffusion_checkpoint(args.v2, args.save_to, text_encoder, unet,
+                                                args.sd_model, 0, 0, save_dtype, vae)
+  else:
+    state_dict = merge_lora_models(args.models, args.ratios, merge_dtype)
+
+    print(f"saving model to: {args.save_to}")
+    save_to_file(args.save_to, state_dict, state_dict, save_dtype)
+
+
+if __name__ == '__main__':
+  parser = argparse.ArgumentParser()
+  parser.add_argument("--v2", action='store_true',
+                      help='load Stable Diffusion v2.x model / Stable Diffusion 2.xのモデルを読み込む')
+  parser.add_argument("--save_precision", type=str, default=None,
+                      choices=[None, "float", "fp16", "bf16"], help="precision in saving, same to merging if omitted / 保存時に精度を変更して保存する、省略時はマージ時の精度と同じ")
+  parser.add_argument("--precision", type=str, default="float",
+                      choices=["float", "fp16", "bf16"], help="precision in merging / マージの計算時の精度")
+  parser.add_argument("--sd_model", type=str, default=None,
+                      help="Stable Diffusion model to load: ckpt or safetensors file, merge LoRA models if omitted / 読み込むモデル、ckptまたはsafetensors。省略時はLoRAモデル同士をマージする")
+  parser.add_argument("--save_to", type=str, default=None,
+                      help="destination file name: ckpt or safetensors file / 保存先のファイル名、ckptまたはsafetensors")
+  parser.add_argument("--models", type=str, nargs='*',
+                      help="LoRA models to merge: ckpt or safetensors file / マージするLoRAモデル、ckptまたはsafetensors")
+  parser.add_argument("--ratios", type=float, nargs='*',
+                      help="ratios for each model / それぞれのLoRAモデルの比率")
+
+  args = parser.parse_args()
+  merge(args)