AttributeError: 'NoneType' object has no attribute 'to'。 How should I do? Thanks a lot.

[chimelea666]

17:33:18-247491 INFO Training started with config file / 训练开始，使用配置文件: F:\lora-scripts-v1.10.0\config\autosave\20241116-173318.toml
17:33:18-247491 INFO Task 3c7688bb-72ce-4607-b60c-42900dacbf2b created
2024-11-16 17:33:25 INFO Loading settings from F:\lora-scripts-v1.10.0\config\autosave\20241116-173318.toml... train_util.py:4435
INFO F:\lora-scripts-v1.10.0\config\autosave\20241116-173318 train_util.py:4454
2024-11-16 17:33:25 INFO Checking the state dict: Diffusers or BFL, dev or schnell flux_utils.py:62
INFO t5xxl_max_token_length: 512 flux_train_network.py:152
You are using the default legacy behaviour of the <class 'transformers.models.t5.tokenization_t5.T5Tokenizer'>. This is expected, and simply means that the legacy (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set legacy=False. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in huggingface/transformers#24565
2024-11-16 17:33:28 INFO Using DreamBooth method. train_network.py:315
INFO prepare images. train_util.py:1956
INFO get image size from name of cache files train_util.py:1873
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 38/38 [00:00<?, ?it/s]
INFO set image size from cache files: 38/38 train_util.py:1901
INFO found directory F:\lora-scripts\train\10_nml_xl\5_zkz contains 38 image files train_util.py:1903
read caption: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 38/38 [00:00<00:00, 2437.77it/s]
WARNING No caption file found for 1 images. Training will continue without captions for these images. If class token exists, it will be train_util.py:1934
used. / 1枚の画像にキャプションファイルが見つかりませんでした。これらの画像についてはキャプションなしで学習を続行します。class
tokenが存在する場合はそれを使います。
WARNING F:\lora-scripts\train\10_nml_xl\5_zkz\ComfyUI_03235_.png train_util.py:1941
INFO 190 train images with repeating. train_util.py:1997
INFO 0 reg images. train_util.py:2000
WARNING no regularization images / 正則化画像が見つかりませんでした train_util.py:2005
INFO [Dataset 0] config_util.py:567
batch_size: 1
resolution: (768, 896)
enable_bucket: False
network_multiplier: 1.0

                           [Subset 0 of Dataset 0]
                             image_dir: "F:\lora-scripts\train\10_nml_xl\5_zkz"
                             image_count: 38
                             num_repeats: 5
                             shuffle_caption: False
                             keep_tokens: 1
                             keep_tokens_separator:
                             caption_separator: ,
                             secondary_separator: None
                             enable_wildcard: False
                             caption_dropout_rate: 0.0
                             caption_dropout_every_n_epoches: 0
                             caption_tag_dropout_rate: 0.0
                             caption_prefix: None
                             caption_suffix: None
                             color_aug: False
                             flip_aug: True
                             face_crop_aug_range: None
                             random_crop: False
                             token_warmup_min: 1
                             token_warmup_step: 0
                             alpha_mask: False
                             custom_attributes: {}
                             is_reg: False
                             class_tokens: zkz
                             caption_extension: .txt


                INFO     [Dataset 0]                                                                                                                         config_util.py:573
                INFO     loading image sizes.                                                                                                                 train_util.py:923

100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 38/38 [00:00<?, ?it/s]
INFO prepare dataset train_util.py:948
INFO preparing accelerator train_network.py:369
accelerator device: cuda
INFO Checking the state dict: Diffusers or BFL, dev or schnell flux_utils.py:62
INFO Building Flux model dev from BFL checkpoint flux_utils.py:120
INFO Loading state dict from F:/lora-scripts-v1.10.0/sd-models/flux1-dev.safetensors flux_utils.py:137
INFO Loaded Flux: flux_utils.py:156
INFO Building CLIP flux_utils.py:176
INFO Loading state dict from E:/comfyui-auto/models/clip/flux_clip_l.safetensors flux_utils.py:269
INFO Loaded CLIP: flux_utils.py:272
INFO Loading state dict from E:/comfyui-auto/models/clip/t5xxl_fp16.safetensors flux_utils.py:317
INFO Loaded T5xxl: flux_utils.py:320
INFO Building AutoEncoder flux_utils.py:163
INFO Loading state dict from E:/comfyui-auto/models/vae/flux-vae-bf16.safetensors flux_utils.py:168
INFO Loaded AE: flux_utils.py:171
import network module: networks.lora_flux
2024-11-16 17:33:29 INFO [Dataset 0] train_util.py:2480
INFO caching latents with caching strategy. train_util.py:1048
INFO caching latents... train_util.py:1093
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 38/38 [00:00<00:00, 2427.26it/s]
INFO move vae and unet to cpu to save memory flux_train_network.py:205
INFO move text encoders to gpu flux_train_network.py:213
2024-11-16 17:33:36 INFO [Dataset 0] train_util.py:2502
INFO caching Text Encoder outputs with caching strategy. train_util.py:1227
INFO checking cache validity... train_util.py:1238
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 38/38 [00:00<00:00, 2431.15it/s]
INFO no Text Encoder outputs to cache train_util.py:1265
INFO move t5XXL back to cpu flux_train_network.py:253
2024-11-16 17:33:39 INFO move vae and unet back to original device flux_train_network.py:258
INFO create LoRA network. base dim (rank): 32, alpha: 16 lora_flux.py:594
INFO neuron dropout: p=None, rank dropout: p=None, module dropout: p=None lora_flux.py:595
INFO train all blocks only lora_flux.py:605
INFO create LoRA for Text Encoder 1: lora_flux.py:741
2024-11-16 17:33:40 INFO create LoRA for Text Encoder 1: 72 modules. lora_flux.py:744
INFO create LoRA for FLUX all blocks: 304 modules. lora_flux.py:765
INFO enable LoRA for text encoder: 72 modules lora_flux.py:911
INFO enable LoRA for U-Net: 304 modules lora_flux.py:916
FLUX: Gradient checkpointing enabled. CPU offload: False
prepare optimizer, data loader etc.
INFO Text Encoder 1 (CLIP-L): 72 modules, LR 1e-05 lora_flux.py:1018
INFO use AdamW optimizer | {} train_util.py:4788
override steps. steps for 40 epochs is / 指定エポックまでのステップ数: 7600
enable full fp16 training.
running training / 学習開始
num train images * repeats / 学習画像の数×繰り返し回数: 190
num reg images / 正則化画像の数: 0
num batches per epoch / 1epochのバッチ数: 190
num epochs / epoch数: 40
batch size per device / バッチサイズ: 1
gradient accumulation steps / 勾配を合計するステップ数 = 1
total optimization steps / 学習ステップ数: 7600
steps: 0%| | 0/7600 [00:00<?, ?it/s]2024-11-16 17:35:07 INFO unet dtype: torch.float16, device: cuda:0 train_network.py:1084
INFO text_encoder [0] dtype: torch.float16, device: cuda:0 train_network.py:1090
INFO text_encoder [1] dtype: torch.float16, device: cpu train_network.py:1090

epoch 1/40
2024-11-16 17:35:57 INFO epoch is incremented. current_epoch: 0, epoch: 1 train_util.py:715
2024-11-16 17:35:57 INFO epoch is incremented. current_epoch: 0, epoch: 1 train_util.py:715
2024-11-16 17:35:57 INFO epoch is incremented. current_epoch: 0, epoch: 1 train_util.py:715
2024-11-16 17:35:57 INFO epoch is incremented. current_epoch: 0, epoch: 1 train_util.py:715
2024-11-16 17:35:57 INFO epoch is incremented. current_epoch: 0, epoch: 1 train_util.py:715
2024-11-16 17:35:57 INFO epoch is incremented. current_epoch: 0, epoch: 1 train_util.py:715
2024-11-16 17:35:57 INFO epoch is incremented. current_epoch: 0, epoch: 1 train_util.py:715
2024-11-16 17:35:57 INFO epoch is incremented. current_epoch: 0, epoch: 1 train_util.py:715
Traceback (most recent call last):
File "F:\lora-scripts-v1.10.0\scripts\dev\flux_train_network.py", line 564, in
trainer.train(args)
File "F:\lora-scripts-v1.10.0\scripts\dev\train_network.py", line 1165, in train
encoded_text_encoder_conds = [c.to(weight_dtype) for c in encoded_text_encoder_conds]
File "F:\lora-scripts-v1.10.0\scripts\dev\train_network.py", line 1165, in
encoded_text_encoder_conds = [c.to(weight_dtype) for c in encoded_text_encoder_conds]
AttributeError: 'NoneType' object has no attribute 'to'
steps: 0%| | 0/7600 [00:52<?, ?it/s]
17:36:01-764187 ERROR Training failed / 训练失败