comfyui fail

#1
by hf666 - opened

I have set the clip correctly, but I am getting the following error:

KSampler
mat1 and mat2 shapes cannot be multiplied (13770x1536 and 768x1536)

TIPS: If you have any "Load CLIP" or "*CLIP Loader" nodes in your workflow connected to this sampler node make sure the correct file(s) and type is selected.

。。。。。。
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_portable_TE_v251207\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
File "E:\ComfyUI_portable_TE_v251207\ComfyUI\comfy\ldm\wan\model.py", line 244, in forward
y = self.self_attn(
torch.addcmul(repeat_e(e[0], x), self.norm1(x), 1 + repeat_e(e[1], x)),
freqs, transformer_options=transformer_options)
File "E:\ComfyUI_portable_TE_v251207\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_portable_TE_v251207\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
File "E:\ComfyUI_portable_TE_v251207\ComfyUI\comfy\ldm\wan\model.py", line 80, in forward
q = qkv_fn_q(x)
File "E:\ComfyUI_portable_TE_v251207\ComfyUI\comfy\ldm\wan\model.py", line 70, in qkv_fn_q
q = self.norm_q(self.q(x)).view(b, s, n, d)
~~~~~~^^^
File "E:\ComfyUI_portable_TE_v251207\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_portable_TE_v251207\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
File "E:\ComfyUI_portable_TE_v251207\ComfyUI\comfy\ops.py", line 358, in forward
return self.forward_comfy_cast_weights(*args, **kwargs)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_portable_TE_v251207\ComfyUI\comfy\ops.py", line 351, in forward_comfy_cast_weights
x = torch.nn.functional.linear(input, weight, bias)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (13770x1536 and 768x1536)

comfyui lumi batcher overwrite task done
Prompt executed in 0.31 seconds

Self-Forcing-NVFP4 (LightX2V) β€” Inference Notes

Thank you for your interest in Self-Forcing-NVFP4 from the LightX2V team.

At the moment, inference via ComfyUI is not supported.
In the meantime, you can run inference directly with LightX2V by referring to the following config:

Sign up or log in to comment