TypeError: linear(): argument 'weight' (position 2) must be Tensor, not NoneType

[auricomborder-sketch]

Receiving the following error on generation with Z Image:

Traceback (most recent call last):
File "D:\AI\ChromaForge\chromaforge\modules_forge\main_thread.py", line 30, in work
self.result = self.func(*self.args, **self.kwargs)
File "D:\AI\ChromaForge\chromaforge\modules\txt2img.py", line 131, in txt2img_function
processed = processing.process_images(p)
File "D:\AI\ChromaForge\chromaforge\modules\processing.py", line 847, in process_images
res = process_images_inner(p)
File "D:\AI\ChromaForge\chromaforge\modules\processing.py", line 1003, in process_images_inner
samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
File "D:\AI\ChromaForge\chromaforge\modules\processing.py", line 1400, in sample
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
File "D:\AI\ChromaForge\chromaforge\modules\sd_samplers_kdiffusion.py", line 242, in sample
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "D:\AI\ChromaForge\chromaforge\modules\sd_samplers_common.py", line 287, in launch_sampling
return func()
File "D:\AI\ChromaForge\chromaforge\modules\sd_samplers_kdiffusion.py", line 242, in
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "D:\AI\ChromaForge\chromaforge\venv\lib\site-packages\torch\utils_contextlib.py", line 120, in decorate_context
return func(*args, **kwargs)
File "D:\AI\ChromaForge\chromaforge\k_diffusion\sampling.py", line 150, in sample_euler
denoised = model(x, sigma_hat * s_in, **extra_args)
File "D:\AI\ChromaForge\chromaforge\venv\lib\site-packages\torch\nn\modules\module.py", line 1773, in _wrapped_call_impl
return self.call_impl(*args, **kwargs)
File "D:\AI\ChromaForge\chromaforge\venv\lib\site-packages\torch\nn\modules\module.py", line 1784, in call_impl
return forward_call(*args, **kwargs)
File "D:\AI\ChromaForge\chromaforge\modules\sd_samplers_cfg_denoiser.py", line 199, in forward
denoised, cond_pred, uncond_pred = sampling_function(self, denoiser_params=denoiser_params, cond_scale=cond_scale, cond_composition=cond_composition)
File "D:\AI\ChromaForge\chromaforge\backend\sampling\sampling_function.py", line 364, in sampling_function
denoised, cond_pred, uncond_pred = sampling_function_inner(model, x, timestep, uncond, cond, cond_scale, model_options, seed, return_full=True)
File "D:\AI\ChromaForge\chromaforge\backend\sampling\sampling_function.py", line 305, in sampling_function_inner
cond_pred, uncond_pred = calc_cond_uncond_batch(model, cond, uncond, x, timestep, model_options)
File "D:\AI\ChromaForge\chromaforge\backend\sampling\sampling_function.py", line 275, in calc_cond_uncond_batch
output = model.apply_model(input_x, timestep, **c).chunk(batch_chunks)
File "D:\AI\ChromaForge\chromaforge\backend\modules\k_model.py", line 77, in apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
File "D:\AI\ChromaForge\chromaforge\venv\lib\site-packages\torch\nn\modules\module.py", line 1773, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\AI\ChromaForge\chromaforge\venv\lib\site-packages\torch\nn\modules\module.py", line 1784, in _call_impl
return forward_call(*args, **kwargs)
File "D:\AI\ChromaForge\chromaforge\backend\diffusion_engine\zimage.py", line 163, in forward
result = self.transformer(x=x, t=timestep, cap_feats=context, patch_size=2, f_patch_size=1)
File "D:\AI\ChromaForge\chromaforge\venv\lib\site-packages\torch\nn\modules\module.py", line 1773, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\AI\ChromaForge\chromaforge\venv\lib\site-packages\torch\nn\modules\module.py", line 1784, in _call_impl
return forward_call(*args, **kwargs)
File "D:\AI\ChromaForge\chromaforge\venv\lib\site-packages\diffusers\models\transformers\transformer_z_image.py", line 585, in forward
x = self.all_x_embedderf"{patch_size}-{f_patch_size}"
File "D:\AI\ChromaForge\chromaforge\venv\lib\site-packages\torch\nn\modules\module.py", line 1773, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\AI\ChromaForge\chromaforge\venv\lib\site-packages\torch\nn\modules\module.py", line 1784, in _call_impl
return forward_call(*args, **kwargs)
File "D:\AI\ChromaForge\chromaforge\backend\operations.py", line 129, in forward
return torch.nn.functional.linear(x, weight, bias)
TypeError: linear(): argument 'weight' (position 2) must be Tensor, not NoneType
linear(): argument 'weight' (position 2) must be Tensor, not NoneType

[maybleMyers]

i think you may have downloaded the wrong model. Where did you get it from?

[auricomborder-sketch]

i think you may have downloaded the wrong model. Where did you get it from?

Got it from here: https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files

Works fine on Comfy, does Forge require a different version?

[wideload1971]

i think you may have downloaded the wrong model. Where did you get it from?

Got it from here: https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files

Works fine on Comfy, does Forge require a different version?

I've just had the same error with files from that location. This link is posted on the main github page and I'm downloading them to try out. You may want to do the same.
https://huggingface.co/maybleMyers/z-image/tree/main

[maybleMyers]

I pushed a fix to check for their layer names and convert them back to diffusers format during loading. They renamed the layers.