hello - 'SDXL' object has no attribute 'get_model_object'- can you help me

[nikolaiusa]

Error occurred when executing Iterative Mixing KSampler:

'SDXL' object has no attribute 'get_model_object'

File "I:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "I:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "I:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "I:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Iterative-Mixer\nodes.py", line 740, in sample
(z_primes,) = self.batch_unsampler.unsampler(model, sampler_name,
File "I:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "I:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Iterative-Mixer\nodes.py", line 173, in unsampler
sigmas = calc_sigmas(model, sampler_name, scheduler, steps,
File "I:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "I:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Iterative-Mixer\nodes.py", line 33, in calc_sigmas
sampler = comfy.samplers.KSampler(real_model, steps=steps, device=device, sampler=sampler_name, scheduler=scheduler, denoise=1.0, model_options=model.model_options)
File "I:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 767, in init
self.set_steps(steps, denoise)
File "I:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 788, in set_steps
self.sigmas = self.calculate_sigmas(steps).to(self.device)
File "I:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 779, in calculate_sigmas
sigmas = calculate_sigmas(self.model.get_model_object("model_sampling"), self.scheduler, steps)
File "I:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1709, in getattr
raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")

[HMBM47]

The same issue can be fixed with the same changes made here to lines 30-33 of nodes.py:
BlenderNeko/ComfyUI_Noise@5cd95f7

[ttulttul]

Sigh, yes this happens because of a breaking change made to ComfyUI a few months ago. I did not fix it comprehensively and will try to get to this soon. Sorry.

[ModzhaHead]

i have a same error, but maybe i doing something wrong in workflow design?
question to owner - can you share workflow from article? maybe it works as it should and we misunderstood something and that's why we're getting errors?

[ttulttul]

@ModzhaHead Would you mind sharing your workflow here? I think I know why this is happening but I'd love the JSON file so that I can replicate it precisely.

[ModzhaHead]

Would you mind sharing your workflow here? I think I know why this is happening but I'd love the JSON file so that I can replicate it precisely.

I may have been unclear... I meant that I am asking the developer to share the workflow described in the article