Unable to run the code for training HunyuanDiT：AttributeError: 'NoneType' object has no attribute 'train'

export CUDA_VISIBLE_DEVICES="0"
python examples/train/hunyuan_dit/train_hunyuan_dit_lora.py --pretrained_path /home/ps/AI/images/Tencent-Hunyuan/HunyuanDiT-v1.2/t2i --dataset_path /home/ps/AI/video2/lora/DiffSynth-Studio/lora-stable-diffusion-finetune/data/dog --output_path /home/ps/AI/video2/lora/DiffSynth-Studio/lora-stable-diffusion-finetune/output --max_epochs 1 --steps_per_epoch 500 --height 1024 --width 1024 --center_crop --precision "16-mixed" --learning_rate 1e-4 --lora_rank 4 --lora_alpha 4 --use_gradient_checkpointing

Always prompt the following error message：

Loading models from: /home/ps/AI/images/Tencent-Hunyuan/HunyuanDiT-v1.2/t2i/clip_text_encoder/pytorch_model.bin
model_name: hunyuan_dit_clip_text_encoder model_class: HunyuanDiTCLIPTextEncoder
The following models are loaded: ['hunyuan_dit_clip_text_encoder'].
Loading models from: /home/ps/AI/images/Tencent-Hunyuan/HunyuanDiT-v1.2/t2i/mt5/pytorch_model.bin
model_name: hunyuan_dit_t5_text_encoder model_class: HunyuanDiTT5TextEncoder
The following models are loaded: ['hunyuan_dit_t5_text_encoder'].
Loading models from: /home/ps/AI/images/Tencent-Hunyuan/HunyuanDiT-v1.2/t2i/model/pytorch_model_ema.pt
We cannot detect the model type. No models are loaded.
Loading models from: /home/ps/AI/images/Tencent-Hunyuan/HunyuanDiT-v1.2/t2i/sdxl-vae-fp16-fix/diffusion_pytorch_model.bin
model_name: sdxl_vae_encoder model_class: SDXLVAEEncoder
This model is initialized with extra kwargs: {'upcast_to_float32': True}
model_name: sdxl_vae_decoder model_class: SDXLVAEDecoder
This model is initialized with extra kwargs: {'upcast_to_float32': True}
The following models are loaded: ['sdxl_vae_encoder', 'sdxl_vae_decoder'].
Using hunyuan_dit_clip_text_encoder from /home/ps/AI/images/Tencent-Hunyuan/HunyuanDiT-v1.2/t2i/clip_text_encoder/pytorch_model.bin.
Using hunyuan_dit_t5_text_encoder from /home/ps/AI/images/Tencent-Hunyuan/HunyuanDiT-v1.2/t2i/mt5/pytorch_model.bin.
No hunyuan_dit models available.
Using sdxl_vae_decoder from /home/ps/AI/images/Tencent-Hunyuan/HunyuanDiT-v1.2/t2i/sdxl-vae-fp16-fix/diffusion_pytorch_model.bin.
Using sdxl_vae_encoder from /home/ps/AI/images/Tencent-Hunyuan/HunyuanDiT-v1.2/t2i/sdxl-vae-fp16-fix/diffusion_pytorch_model.bin.
Traceback (most recent call last):
File "/home/ps/disk/nvme1TB/AI/video2/lora/DiffSynth-Studio/examples/train/hunyuan_dit/train_hunyuan_dit_lora.py", line 54, in
model = LightningModel(
File "/home/ps/disk/nvme1TB/AI/video2/lora/DiffSynth-Studio/examples/train/hunyuan_dit/train_hunyuan_dit_lora.py", line 21, in init
self.freeze_parameters()
File "/home/ps/disk/nvme1TB/AI/video2/DiffSynth-Studio-1.1.7/diffsynth/trainers/text_to_image.py", line 34, in freeze_parameters
self.pipe.denoising_model().train()
AttributeError: 'NoneType' object has no attribute 'train'

Reproduce the command from the issue and inspect examples/train/hunyuan_dit/train_hunyuan_dit_lora.py alongside diffsynth/trainers/text_to_image.py. Start with the model-loading output showing that no hunyuan_dit model is loaded, then trace the denoising_model() call. Done means the HunyuanDiT model is recognized and training starts without the NoneType train error.