LTX-2.3 will train on images but not video... LTX-2 appears to be broken.

[Brentron1982]

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

• 0 completed jobs
• 1 failure
  ========================================
  Traceback (most recent call last):
  Traceback (most recent call last):
  File "/app/ai-toolkit/run.py", line 120, in
  File "/app/ai-toolkit/run.py", line 120, in
  main()main()
  File "/app/ai-toolkit/run.py", line 108, in main
  File "/app/ai-toolkit/run.py", line 108, in main
  raise eraise e
  File "/app/ai-toolkit/run.py", line 96, in main
  File "/app/ai-toolkit/run.py", line 96, in main
  job.run()job.run()
  File "/app/ai-toolkit/jobs/ExtensionJob.py", line 22, in run
  File "/app/ai-toolkit/jobs/ExtensionJob.py", line 22, in run
  process.run()process.run()
  File "/app/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 2216, in run
  File "/app/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 2216, in run
  loss_dict = self.hook_train_loop(batch_list)loss_dict = self.hook_train_loop(batch_list)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/ai-toolkit/extensions_built_in/sd_trainer/SDTrainer.py", line 2071, in hook_train_loop
  File "/app/ai-toolkit/extensions_built_in/sd_trainer/SDTrainer.py", line 2071, in hook_train_loop
  loss = self.train_single_accumulation(batch)loss = self.train_single_accumulation(batch)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/ai-toolkit/extensions_built_in/sd_trainer/SDTrainer.py", line 1967, in train_single_accumulation
  File "/app/ai-toolkit/extensions_built_in/sd_trainer/SDTrainer.py", line 1967, in train_single_accumulation
  noise_pred = self.predict_noise(noise_pred = self.predict_noise(
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/ai-toolkit/extensions_built_in/sd_trainer/SDTrainer.py", line 1204, in predict_noise
  File "/app/ai-toolkit/extensions_built_in/sd_trainer/SDTrainer.py", line 1204, in predict_noise
  return self.sd.predict_noise(return self.sd.predict_noise(
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/ai-toolkit/toolkit/models/base_model.py", line 926, in predict_noise
  File "/app/ai-toolkit/toolkit/models/base_model.py", line 926, in predict_noise
  noise_pred = self.get_noise_prediction(noise_pred = self.get_noise_prediction(
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/ai-toolkit/extensions_built_in/diffusion_models/ltx2/ltx2.py", line 963, in get_noise_prediction
  File "/app/ai-toolkit/extensions_built_in/diffusion_models/ltx2/ltx2.py", line 963, in get_noise_prediction
  noise_pred_video, noise_pred_audio = self.transformer(noise_pred_video, noise_pred_audio = self.transformer(
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
  return self._call_impl(*args, **kwargs)return self._call_impl(*args, **kwargs)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1786, in _call_impl
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1786, in _call_impl
  return forward_call(*args, **kwargs)return forward_call(*args, **kwargs)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/diffusers/utils/peft_utils.py", line 315, in wrapper
  File "/usr/local/lib/python3.12/dist-packages/diffusers/utils/peft_utils.py", line 315, in wrapper
  result = forward_fn(self, *args, **kwargs)result = forward_fn(self, *args, **kwargs)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/diffusers/models/transformers/transformer_ltx2.py", line 1552, in forward
  File "/usr/local/lib/python3.12/dist-packages/diffusers/models/transformers/transformer_ltx2.py", line 1552, in forward
  hidden_states, audio_hidden_states = self._gradient_checkpointing_func(hidden_states, audio_hidden_states = self._gradient_checkpointing_func(
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/diffusers/models/modeling_utils.py", line 303, in _gradient_checkpointing_func
  File "/usr/local/lib/python3.12/dist-packages/diffusers/models/modeling_utils.py", line 303, in _gradient_checkpointing_func
  return torch.utils.checkpoint.checkpoint(return torch.utils.checkpoint.checkpoint(
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/_compile.py", line 53, in inner
  File "/usr/local/lib/python3.12/dist-packages/torch/_compile.py", line 53, in inner
  return disable_fn(*args, **kwargs)return disable_fn(*args, **kwargs)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/_dynamo/eval_frame.py", line 1044, in _fn
  File "/usr/local/lib/python3.12/dist-packages/torch/_dynamo/eval_frame.py", line 1044, in _fn
  return fn(*args, **kwargs)return fn(*args, **kwargs)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py", line 503, in checkpoint
  File "/usr/local/lib/python3.12/dist-packages/torch/utils/checkpoint.py", line 503, in checkpoint
  ret = function(*args, **kwargs)ret = function(*args, **kwargs)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
  return self._call_impl(*args, **kwargs)return self._call_impl(*args, **kwargs)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1786, in _call_impl
  File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1786, in _call_impl
  return forward_call(*args, **kwargs)return forward_call(*args, **kwargs)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/diffusers/models/transformers/transformer_ltx2.py", line 688, in forward
  File "/usr/local/lib/python3.12/dist-packages/diffusers/models/transformers/transformer_ltx2.py", line 688, in forward
  encoder_hidden_states = encoder_hidden_states * (1 + scale_text_kv) + shift_text_kvencoder_hidden_states = encoder_hidden_states * (1 + scale_text_kv) + shift_text_kv
  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  RuntimeErrorRuntimeError: : The size of tensor a (1024) must match the size of tensor b (4032) at non-singleton dimension 1The size of tensor a (1024) must match the size of tensor b (4032) at non-singleton dimension 1

[jaretburkett]

This should be fixed now.