Error(s) in loading state_dict for UNet2DConditionModel

[CliffordJordan]

I keep getting this error with Realistic Vision 2.0 and Paragon 1.0. However, when I use Realistic Vision 1.3, there is no such and all works well.

Here is the error...
prepare tokenizer
Use DreamBooth method.
prepare images.
found directory C:\ai\kohya_ss\Lora Training Data\deisegataD\image\200_deisegatad contains 29 image files
5800 train images with repeating.
0 reg images.
no regularization images / 正則化画像が見つかりませんでした
[Dataset 0]
batch_size: 4
resolution: (768, 768)
enable_bucket: True
min_bucket_reso: 256
max_bucket_reso: 1024
bucket_reso_steps: 64
bucket_no_upscale: True

[Subset 0 of Dataset 0]
image_dir: "C:\ai\kohya_ss\Lora Training Data\deisegataD\image\200_deisegatad"
image_count: 29
num_repeats: 200
shuffle_caption: False
keep_tokens: 0
caption_dropout_rate: 0.0
caption_dropout_every_n_epoches: 0
caption_tag_dropout_rate: 0.0
color_aug: False
flip_aug: False
face_crop_aug_range: None
random_crop: False
token_warmup_min: 1,
token_warmup_step: 0,
is_reg: False
class_tokens: deisegatad
caption_extension: .caption

[Dataset 0]
loading image sizes.
100%|████████████████████████████████████████████████████████████████████████████████| 29/29 [00:00<00:00, 4141.75it/s]
make buckets
min_bucket_reso and max_bucket_reso are ignored if bucket_no_upscale is set, because bucket reso is defined by image size automatically / bucket_no_upscaleが指定された場合は、bucketの解像度は画像サイズから自動計算されるため、min_bucket_resoとmax_bucket_resoは無視されます
number of images (including repeats) / 各bucketの画像枚数（繰り返し回数を含む）
bucket 0: resolution (512, 512), count: 5800
mean ar error (without repeats): 0.0
prepare accelerator
C:\ai\kohya_ss\venv\lib\site-packages\accelerate\accelerator.py:249: FutureWarning: logging_dir is deprecated and will be removed in version 0.18.0 of 🤗 Accelerate. Use project_dir instead.
warnings.warn(
Using accelerator 0.15.0 or above.
load args= Namespace(v2=True, v_parameterization=False, pretrained_model_name_or_path='C:/ai/stable-diffusion-webui/models/Stable-diffusion/Paragon_1.0_Beta.safetensors', tokenizer_cache_dir=None, train_data_dir='C:/ai/kohya_ss/Lora Training Data/deisegataD/image', shuffle_caption=False, caption_extension='.caption', caption_extention=None, keep_tokens=0, color_aug=False, flip_aug=False, face_crop_aug_range=None, random_crop=False, debug_dataset=False, resolution=(768, 768), cache_latents=True, vae_batch_size=1, cache_latents_to_disk=False, enable_bucket=True, min_bucket_reso=256, max_bucket_reso=1024, bucket_reso_steps=64, bucket_no_upscale=True, token_warmup_min=1, token_warmup_step=0, caption_dropout_rate=0.0, caption_dropout_every_n_epochs=0, caption_tag_dropout_rate=0.0, reg_data_dir=None, in_json=None, dataset_repeats=1, output_dir='C:/ai/kohya_ss/Lora Training Data/deisegataD/model', output_name='deisegata_d2', huggingface_repo_id=None, huggingface_repo_type=None, huggingface_path_in_repo=None, huggingface_token=None, huggingface_repo_visibility=None, save_state_to_huggingface=False, resume_from_huggingface=False, async_upload=False, save_precision='fp16', save_every_n_epochs=1, save_every_n_steps=None, save_n_epoch_ratio=None, save_last_n_epochs=None, save_last_n_epochs_state=None, save_last_n_steps=None, save_last_n_steps_state=None, save_state=False, resume=None, train_batch_size=4, max_token_length=None, mem_eff_attn=True, xformers=True, vae=None, max_train_steps=1450, max_train_epochs=None, max_data_loader_n_workers=0, persistent_data_loader_workers=False, seed=828459009, gradient_checkpointing=True, gradient_accumulation_steps=1, mixed_precision='fp16', full_fp16=False, clip_skip=None, logging_dir='C:/ai/kohya_ss/Lora Training Data/deisegataD/log', log_with=None, log_prefix=None, log_tracker_name=None, wandb_api_key=None, noise_offset=None, multires_noise_iterations=None, multires_noise_discount=0.3, adaptive_noise_scale=None, lowram=False, sample_every_n_steps=100, sample_every_n_epochs=None, sample_prompts='C:/ai/kohya_ss/Lora Training Data/deisegataD/model\sample\prompt.txt', sample_sampler='euler_a', config_file=None, output_config=False, prior_loss_weight=1.0, optimizer_type='AdamW8bit', use_8bit_adam=False, use_lion_optimizer=False, learning_rate=0.0001, max_grad_norm=1.0, optimizer_args=None, lr_scheduler_type='', lr_scheduler_args=None, lr_scheduler='cosine', lr_warmup_steps=145, lr_scheduler_num_cycles=1, lr_scheduler_power=1, dataset_config=None, min_snr_gamma=None, weighted_captions=False, no_metadata=False, save_model_as='safetensors', unet_lr=0.0001, text_encoder_lr=5e-05, network_weights=None, network_module='networks.lora', network_dim=8, network_alpha=1.0, network_args=None, network_train_unet_only=False, network_train_text_encoder_only=False, training_comment=None, dim_from_weights=False)
weight_dtype= torch.float16
accelerator= <accelerate.accelerator.Accelerator object at 0x0000021AEC950040>
loading model for process 0/1
load StableDiffusion checkpoint: C:/ai/stable-diffusion-webui/models/Stable-diffusion/Paragon_1.0_Beta.safetensors
Traceback (most recent call last):
File "C:\ai\kohya_ss\train_network.py", line 790, in
train(args)
File "C:\ai\kohya_ss\train_network.py", line 149, in train
text_encoder, vae, unet, _ = train_util.load_target_model(args, weight_dtype, accelerator)
File "C:\ai\kohya_ss\library\train_util.py", line 3023, in load_target_model
text_encoder, vae, unet, load_stable_diffusion_format = _load_target_model(
File "C:\ai\kohya_ss\library\train_util.py", line 2989, in _load_target_model
text_encoder, vae, unet = model_util.load_models_from_stable_diffusion_checkpoint(args.v2, name_or_path, device)
File "C:\ai\kohya_ss\library\model_util.py", line 863, in load_models_from_stable_diffusion_checkpoint
info = unet.load_state_dict(converted_unet_checkpoint)
File "C:\ai\kohya_ss\venv\lib\site-packages\torch\nn\modules\module.py", line 1604, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for UNet2DConditionModel:
size mismatch for down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([320, 768]) from checkpoint, the shape in current model is torch.Size([320, 1024]).
size mismatch for down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([320, 768]) from checkpoint, the shape in current model is torch.Size([320, 1024]).
size mismatch for down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([320, 768]) from checkpoint, the shape in current model is torch.Size([320, 1024]).
size mismatch for down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([320, 768]) from checkpoint, the shape in current model is torch.Size([320, 1024]).
size mismatch for down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([640, 768]) from checkpoint, the shape in current model is torch.Size([640, 1024]).
size mismatch for down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([640, 768]) from checkpoint, the shape in current model is torch.Size([640, 1024]).
size mismatch for down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([640, 768]) from checkpoint, the shape in current model is torch.Size([640, 1024]).
size mismatch for down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([640, 768]) from checkpoint, the shape in current model is torch.Size([640, 1024]).
size mismatch for down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([1280, 768]) from checkpoint, the shape in current model is torch.Size([1280, 1024]).
size mismatch for down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([1280, 768]) from checkpoint, the shape in current model is torch.Size([1280, 1024]).
size mismatch for down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([1280, 768]) from checkpoint, the shape in current model is torch.Size([1280, 1024]).
size mismatch for down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([1280, 768]) from checkpoint, the shape in current model is torch.Size([1280, 1024]).
size mismatch for up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([1280, 768]) from checkpoint, the shape in current model is torch.Size([1280, 1024]).
size mismatch for up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([1280, 768]) from checkpoint, the shape in current model is torch.Size([1280, 1024]).
size mismatch for up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([1280, 768]) from checkpoint, the shape in current model is torch.Size([1280, 1024]).
size mismatch for up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([1280, 768]) from checkpoint, the shape in current model is torch.Size([1280, 1024]).
size mismatch for up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([1280, 768]) from checkpoint, the shape in current model is torch.Size([1280, 1024]).
size mismatch for up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([1280, 768]) from checkpoint, the shape in current model is torch.Size([1280, 1024]).
size mismatch for up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([640, 768]) from checkpoint, the shape in current model is torch.Size([640, 1024]).
size mismatch for up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([640, 768]) from checkpoint, the shape in current model is torch.Size([640, 1024]).
size mismatch for up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([640, 768]) from checkpoint, the shape in current model is torch.Size([640, 1024]).
size mismatch for up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([640, 768]) from checkpoint, the shape in current model is torch.Size([640, 1024]).
size mismatch for up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([640, 768]) from checkpoint, the shape in current model is torch.Size([640, 1024]).
size mismatch for up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([640, 768]) from checkpoint, the shape in current model is torch.Size([640, 1024]).
size mismatch for up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([320, 768]) from checkpoint, the shape in current model is torch.Size([320, 1024]).
size mismatch for up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([320, 768]) from checkpoint, the shape in current model is torch.Size([320, 1024]).
size mismatch for up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([320, 768]) from checkpoint, the shape in current model is torch.Size([320, 1024]).
size mismatch for up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([320, 768]) from checkpoint, the shape in current model is torch.Size([320, 1024]).
size mismatch for up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([320, 768]) from checkpoint, the shape in current model is torch.Size([320, 1024]).
size mismatch for up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([320, 768]) from checkpoint, the shape in current model is torch.Size([320, 1024]).
size mismatch for mid_block.attentions.0.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([1280, 768]) from checkpoint, the shape in current model is torch.Size([1280, 1024]).
size mismatch for mid_block.attentions.0.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([1280, 768]) from checkpoint, the shape in current model is torch.Size([1280, 1024]).
Traceback (most recent call last):
File "C:\Users\cliff.RICHARDFEYNMAN\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\cliff.RICHARDFEYNMAN\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "C:\ai\kohya_ss\venv\Scripts\accelerate.exe_main.py", line 7, in
File "C:\ai\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main
args.func(args)
File "C:\ai\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 923, in launch_command
simple_launcher(args)
File "C:\ai\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 579, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['C:\ai\kohya_ss\venv\Scripts\python.exe', 'train_network.py', '--v2', '--enable_bucket', '--pretrained_model_name_or_path=C:/ai/stable-diffusion-webui/models/Stable-diffusion/Paragon_1.0_Beta.safetensors', '--train_data_dir=C:/ai/kohya_ss/Lora Training Data/deisegataD/image', '--resolution=768,768', '--output_dir=C:/ai/kohya_ss/Lora Training Data/deisegataD/model', '--logging_dir=C:/ai/kohya_ss/Lora Training Data/deisegataD/log', '--network_alpha=1', '--save_model_as=safetensors', '--network_module=networks.lora', '--text_encoder_lr=5e-05', '--unet_lr=0.0001', '--network_dim=8', '--output_name=deisegata_d2', '--lr_scheduler_num_cycles=1', '--learning_rate=0.0001', '--lr_scheduler=cosine', '--lr_warmup_steps=145', '--train_batch_size=4', '--max_train_steps=1450', '--save_every_n_epochs=1', '--mixed_precision=fp16', '--save_precision=fp16', '--cache_latents', '--optimizer_type=AdamW8bit', '--max_data_loader_n_workers=0', '--bucket_reso_steps=64', '--mem_eff_attn', '--gradient_checkpointing', '--xformers', '--bucket_no_upscale', '--sample_sampler=euler_a', '--sample_prompts=C:/ai/kohya_ss/Lora Training Data/deisegataD/model\sample\prompt.txt', '--sample_every_n_steps=100']' returned non-zero exit status 1.