Kijai

/

LTX2.3_comfy

like 271

any suggestions, any one?

The model and clip are the right ones, your workflow has some correct nodes but there are a few things missing. You just need another workflow.

Start here ( https://huggingface.co/RuneXX/LTX-2.3-Workflows/tree/main ) with Basic Image or Text to Video:

https://huggingface.co/RuneXX/LTX-2.3-Workflows/blob/main/LTX-2.3_-_I2V_T2V_Basic.json

Replace the upscaler 1.0 in that workflow with the updated one: https://huggingface.co/Lightricks/LTX-2.3/blob/main/ltx-2.3-spatial-upscaler-x2-1.1.safetensors

The model and clip are the right ones, your workflow has some correct nodes but there are a few things missing. You just need another workflow.

Start here ( https://huggingface.co/RuneXX/LTX-2.3-Workflows/tree/main ) with Basic Image or Text to Video:

https://huggingface.co/RuneXX/LTX-2.3-Workflows/blob/main/LTX-2.3_-_I2V_T2V_Basic.json

Replace the upscaler 1.0 in that workflow with the updated one: https://huggingface.co/Lightricks/LTX-2.3/blob/main/ltx-2.3-spatial-upscaler-x2-1.1.safetensors

i have tried that and have same error, then i made basic one my self. and same error

Your workflow has almost no similarity to the one from RuneXX. In your workflow's error log a node tries to offset two tensors (addition, multiplication, noise-scaling, etc.) whose latent dimensions do not match. And not only slightly different, but completely different sizes:
15810 is extremely small
2055936 is a typical size of an SD latent (e.g. 64×64×4 or 96×96×4)
This is a clear indication: A node provides a latent in false form or false resolution.

But why? WHERE happens the crash? Why do you use comfyui_smznodes and ComfyUI-TiledDiffusion ? They are not in RuneXX's workflow and you cannot have the same error messages with it because it doesn't use the custom-nodes you have: those "smz_nodes" were last updated almost a year ago, the "ComfyUI-TiledDiffusion" two years ago - but LTX 2.3 is just two months old! You can't build a workflow for LTX2.3 with vintage custom-nodes. Try the one from RuneXX again and then copy-and-paste the error log. I'm certain the error messages are not the same.

Now this is same workflow from RuneXX, only updated models

here is the error -
RuntimeError: The size of tensor a (15810) must match the size of tensor b (2055936) at non-singleton dimension 2

File "D:\000AI\00ComfyUI\ComfyUI\execution.py", line 534, 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:\000AI\00ComfyUI\ComfyUI\execution.py", line 334, 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:\000AI\00ComfyUI\ComfyUI\execution.py", line 308, in _async_map_node_over_list
await process_inputs(input_dict, i)

File "D:\000AI\00ComfyUI\ComfyUI\execution.py", line 296, in process_inputs
result = f(**inputs)
^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\comfy_api\internal_init_.py", line 149, in wrapped_func
return method(locked_class, **inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\comfy_api\latest_io.py", line 1789, in EXECUTE_NORMALIZED
to_return = cls.execute(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\comfy_extras\nodes_custom_sampler.py", line 963, in execute
samples = guider.sample(noise.generate_noise(latent), latent_image, sampler, sigmas, denoise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=noise.seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\comfy\samplers.py", line 1052, in sample
output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\comfy\patcher_extension.py", line 113, in execute
return self.wrappers[self.idx](self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\custom_nodes\comfyui-kjnodes\nodes\ltxv_nodes.py", line 878, in call
out = executor(noise, latent_image, sampler, sigmas, denoise_mask, combined_callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\comfy\patcher_extension.py", line 105, in call
return new_executor.execute(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\comfy\patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\comfy\samplers.py", line 995, in outer_sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\comfy\samplers.py", line 981, in inner_sample
samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\comfy\patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\custom_nodes\comfyui_smznodes\smZNodes.py", line 114, in KSAMPLER_sample
return orig_fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\custom_nodes\ComfyUI-TiledDiffusion\utils.py", line 34, in KSAMPLER_sample
return orig_fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\comfy\samplers.py", line 744, in sample
noise = model_wrap.inner_model.model_sampling.noise_scaling(sigmas[0], noise, latent_image, self.max_denoise(model_wrap, sigmas))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\000AI\00ComfyUI\ComfyUI\comfy\model_sampling.py", line 72, in noise_scaling
return sigma * noise + (1.0 - sigma) * latent_image
~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

do u have anything to suggest now?

no suggestion?