PiD v1.5 undistilled vs distilled checkpoint sampler bug

### Custom Node Testing

- [x] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

Using the PiD upscale workflow from ComfyUI templates, the workflow works just fine when PiD checkpoint uses distilled with cfg = 1 and steps = 4. I wanted to try the undistilled checkpoint to see if there is quality improvement so I followed PiD official docs to use undistilled checkpoint with cfg = 5 and steps = 25, everything else left unchanged, it threw an error see below.

### Actual Behavior

Failed to run same workflow when checkpoint changes from distilled to undistilled, and cfg and steps changed too.

### Steps to Reproduce

Use the PiD upscaler template workflow found in ComfyUI templates. Change the PiD checkpoint to v1.5 distilled and undistilled to see that undistilled does not work.

### Debug Logs

```powershell
[ERROR] !!! Exception during processing !!! PidNet requires lq_latent — attach via PiDConditioning
[ERROR] Traceback (most recent call last):
File "/app/ComfyUI/execution.py", line 543, 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 "/app/ComfyUI/execution.py", line 342, 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 "/app/ComfyUI/execution.py", line 316, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "/app/ComfyUI/execution.py", line 304, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "/app/ComfyUI/comfy_api/internal/__init__.py", line 149, in wrapped_func
return method(locked_class, **inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy_api/latest/_io.py", line 1935, in EXECUTE_NORMALIZED
to_return = cls.execute(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy_extras/nodes_custom_sampler.py", line 771, in execute
samples = comfy.sample.sample_custom(model, noise, cfg, sampler, sigmas, positive, negative, latent_image, noise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=noise_seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/sample.py", line 79, in sample_custom
samples = comfy.samplers.sample(model, noise, positive, negative, cfg, model.load_device, sampler, sigmas, model_options=model.model_options, latent_image=latent_image, denoise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 1334, in sample
return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 1316, in sample
output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 1254, in outer_sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 1229, in inner_sample
samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 999, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/python3.12.13/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 124, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/k_diffusion/sampling.py", line 1030, in sample_lcm
denoised = model(x, sigmas[i] * s_in, **extra_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 639, in __call__
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 1202, in __call__
return self.outer_predict_noise(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 1209, in outer_predict_noise
).execute(x, timestep, model_options, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 1212, in predict_noise
return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 619, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 210, in calc_cond_batch
return _calc_cond_batch_outer(model, conds, x_in, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 218, in _calc_cond_batch_outer
return executor.execute(model, conds, x_in, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/samplers.py", line 334, in _calc_cond_batch
output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/model_base.py", line 193, in apply_model
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/model_base.py", line 237, in _apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/python3.12.13/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1778, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/python3.12.13/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1789, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/ldm/pixeldit/model.py", line 192, in forward
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/patcher_extension.py", line 113, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/ComfyUI/comfy/ldm/pixeldit/pid.py", line 236, in _forward
raise ValueError("PidNet requires lq_latent — attach via PiDConditioning")
ValueError: PidNet requires lq_latent — attach via PiDConditioning
```

### Other

_No response_

Start with comfy/ldm/pixeldit/pid.py, where the reported PidNet error is raised, then trace the PiDConditioning path from the PiD upscaler template and comfy_extras/nodes_custom_sampler.py. Reproduce with the distilled and undistilled checkpoints using the stated CFG and step values; done means the undistilled workflow completes without the lq_latent error.

Written by the indexing model from the issue text.