Kijai

/

LTXV2_comfy

like 388

Using the node as show on frontpage on this repo? the Vae KJ node for the audio vae.
https://huggingface.co/Kijai/LTXV2_comfy

im getting Missing weight for layer gemma3_12b.transformer.model.layers.0.self_attn.q_proj

im getting Missing weight for layer gemma3_12b.transformer.model.layers.0.self_attn.q_proj

This one needs comfyui very latest nightly version, it was fixed within last 24h.

Just a FYI , just don't forget to update the KJnodes in the comfyui manager to mine was out of that nad gave same issue

Using the node as show on frontpage on this repo? the Vae KJ node for the audio vae.
https://huggingface.co/Kijai/LTXV2_comfy

i use the gguf

Did this and thank you both. I was able to get it updated, and get through that error. Now I'm facing a new one I can't figure out how to solve:

CUDA error: no kernel image is available for execution on the device
Search for cudaErrorNoKernelImageForDevice' in https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__TYPES.html for more information. CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with TORCH_USE_CUDA_DSA` to enable device-side assertions.

What I've done so far: Installed the latest CUDA 13.1 and restarted the PC. Same error both before and after.

Not sure about that error. That would be something for the expert ;-)
Kijai or someone else might know

Saw a similar here here: https://github.com/Comfy-Org/ComfyUI/issues/8708
Maybe you need to install torch with cuda in the environment you have for Comfy

Did this and thank you both. I was able to get it updated, and get through that error. Now I'm facing a new one I can't figure out how to solve:

CUDA error: no kernel image is available for execution on the device
Search for cudaErrorNoKernelImageForDevice' in https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__TYPES.html for more information. CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with TORCH_USE_CUDA_DSA` to enable device-side assertions.

What I've done so far: Installed the latest CUDA 13.1 and restarted the PC. Same error both before and after.

Are you using sageattention and does this happen if you don't?

Python version: 3.13.8 (main, Oct 7 2025, 15:31:04) [MSC v.1944 64 bit (AMD64)]
ComfyUI version: 0.9.2
ComfyUI frontend version: 1.36.14
The KJ node has also been updated to the latest version.

has use "VAELoader KJ" node，still throw erreo:

got prompt
!!! Exception during processing !!! 'VAE' object has no attribute 'latent_frequency_bins'
Traceback (most recent call last):
File "D:+AI\uv\313\ComfyUI\execution.py", line 518, 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 "D:+AI\uv\313\ComfyUI\execution.py", line 329, 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 "D:+AI\uv\313\ComfyUI\execution.py", line 303, in async_map_node_over_list
await process_inputs(input_dict, i)
File "D:+AI\uv\313\ComfyUI\execution.py", line 291, in process_inputs
result = f(**inputs)
File "D:+AI\uv\313\ComfyUI\comfy_api\internal_init.py", line 149, in wrapped_func
return method(locked_class, **inputs)
File "D:+AI\uv\313\ComfyUI\comfy_api\latest_io.py", line 1658, in EXECUTE_NORMALIZED
to_return = cls.execute(*args, **kwargs)
File "D:+AI\uv\313\ComfyUI\comfy_extras\nodes_lt_audio.py", line 153, in execute
audio_freq = audio_vae.latent_frequency_bins
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'VAE' object has no attribute 'latent_frequency_bins'

Prompt executed in 0.02 seconds

you have to update comfyui-kjnodes
cd /media/2TB/ComfyUI/custom_nodes/comfyui-kjnodes && git pull