The parameter type of batch in TrainSliderProcess.py does not match the receiving type.

[Ando-Lin]

This is for bugs only

Did you already ask in the discord?

No

You verified that this is a bug and not a feature request or question by asking in the discord?

No

Describe the bug

The partial content printed to the console is as follows:

#############################################

Running job: detail_slider_v1

#############################################

Running 1 process
Loading pipeline components...: 100%|█████████████| 7/7 [00:01<00:00, 4.82it/s]
create LoRA network. base dim (rank): 8, alpha: 4
neuron dropout: p=None, rank dropout: p=None, module dropout: p=None
create LoRA for Text Encoder: 0 modules.
create LoRA for U-Net: 722 modules.
enable LoRA for U-Net
Building prompt cache
Prompt tensors not found. Encoding prompts..
Generating baseline samples before training
detail_slider_v1: 0%| | 0/500 [00:00<?, ?it/s]Error running job: 'list' object has no attribute 'get_caption_list'

========================================
Result:

• 0 completed jobs
• 1 failure
  ========================================
  Traceback (most recent call last):
  File "/kaggle/working/ai-toolkit/run.py", line 90, in
  main()
  File "/kaggle/working/ai-toolkit/run.py", line 86, in main
  raise e
  File "/kaggle/working/ai-toolkit/run.py", line 78, in main
  job.run()
  File "/kaggle/working/ai-toolkit/jobs/TrainJob.py", line 49, in run
  process.run()
  File "/kaggle/working/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 1741, in run
  loss_dict = self.hook_train_loop(batch_list)
  File "/kaggle/working/ai-toolkit/jobs/process/TrainSliderProcess.py", line 338, in hook_train_loop
  noisy_latents, noise, timesteps, conditioned_prompts, imgs = self.process_general_training_batch(batch)
  File "/kaggle/working/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 777, in process_general_training_batch
  prompts = batch.get_caption_list()
  AttributeError: 'list' object has no attribute 'get_caption_list'

When I modified the judgment statement on line 335 of ai-toolkit/jobs/process/TrainSliderProcess.py, it worked normally for a while, then another bug occurred：

Result:

• 0 completed jobs
• 1 failure
  ========================================
  Traceback (most recent call last):
  File "/kaggle/working/ai-toolkit/run.py", line 90, in
  main()
  File "/kaggle/working/ai-toolkit/run.py", line 86, in main
  raise e
  File "/kaggle/working/ai-toolkit/run.py", line 78, in main
  job.run()
  File "/kaggle/working/ai-toolkit/jobs/TrainJob.py", line 49, in run
  process.run()
  File "/kaggle/working/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 1741, in run
  loss_dict = self.hook_train_loop(batch_list)
  File "/kaggle/working/ai-toolkit/jobs/process/TrainSliderProcess.py", line 419, in hook_train_loop
  if batch and batch.mask_tensor is not None:
  AttributeError: 'list' object has no attribute 'mask_tensor'

[Volnovik]

Bump