I'm getting this error trying to use your ltx-2.3-edit-insight-dev-fp8.safetensors in your reference workflow (LTX-2.3-ICLORA-Edit-Official-Model-Version):

TypeError: Got unsupported ScalarType BFloat16

ComfyUI Error Report

Error Details

• Node ID: 5153
• Node Type: CheckpointLoaderSimple
• Exception Type: TypeError
• Exception Message: TypeError: Got unsupported ScalarType BFloat16

Stack Trace

  File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 536, in execute
    output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 336, in get_output_data
    return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 310, in _async_map_node_over_list
    await process_inputs(input_dict, i)

  File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 298, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^

  File "C:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 607, in load_checkpoint
    out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 1740, in load_checkpoint_guess_config
    out = load_state_dict_guess_config(sd, output_vae, output_clip, output_clipvision, embedding_directory, output_model, model_options, te_model_options=te_model_options, metadata=metadata, disable_dynamic=disable_dynamic)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 1857, in load_state_dict_guess_config
    model.load_model_weights(sd, diffusion_model_prefix, assign=model_patcher.is_dynamic())

  File "C:\ComfyUI_windows_portable\ComfyUI\comfy\model_base.py", line 346, in load_model_weights
    m, u = self.diffusion_model.load_state_dict(to_load, strict=False, assign=assign)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 2604, in load_state_dict
    load(self, state_dict)

  File "C:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 2592, in load
    load(child, child_state_dict, child_prefix)  # noqa: F821
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 2592, in load
    load(child, child_state_dict, child_prefix)  # noqa: F821
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 2592, in load
    load(child, child_state_dict, child_prefix)  # noqa: F821
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  [Previous line repeated 1 more time]

  File "C:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 2575, in load
    module._load_from_state_dict(

  File "C:\ComfyUI_windows_portable\ComfyUI\comfy\ops.py", line 1177, in _load_from_state_dict
    _load_quantized_module(self, super()._load_from_state_dict, *args, load_extra_params=True)

  File "C:\ComfyUI_windows_portable\ComfyUI\comfy\ops.py", line 1060, in _load_quantized_module
    layer_conf = json.loads(layer_conf.numpy().tobytes())
                            ^^^^^^^^^^^^^^^^^^

System Information

• ComfyUI Version: 0.22.0
• Arguments: ComfyUI\main.py
• OS: win32
• Python Version: 3.12.9 (tags/v3.12.9:fdb8142, Feb 4 2025, 15:27:58) [MSC v.1942 64 bit (AMD64)]
• Embedded Python: true
• PyTorch Version: 2.8.0+cu128

Devices

• Name: cuda:0 NVIDIA GeForce RTX 4090 : cudaMallocAsync
  • Type: cuda
  • VRAM Total: 25756696576
  • VRAM Free: 24064819200
  • Torch VRAM Total: 67108864
  • Torch VRAM Free: 33554432