Wan 2.2 14B Image to Video Template Error

Using this pre-built template, I am getting a VAE error (see below for full output)
**RuntimeError: Given groups=1, weight of size [5120, 36, 1, 2, 2], expected input[1, 64, 21, 80, 80] to have 36 channels, but got 64 channels instead**

- I've tried portable and windows versions of ComfyUI, with no change
- the 5B version works (Wan 2.2 5B Video Generation template)
- Windows 11/RTX4090 (not the D version)
- Tried with and without extensions
- Updated Visual Studio 2022, Cuda 13 etc.
- Tried with wan2.2_vae.safetensors and wan_2.1_vae.safetensors
- Workflow Template is included but it is from the built-in templates

**System Info**
**ComfyUI:** 0.3.50
**ComfyUI_frontend:** v1.24.4
**OS:** nt
**Python Version:** 3.13.6 (tags/v3.13.6:4e66535, Aug 6 2025, 14:36:00) [MSC v.1944 64 bit (AMD64)]
**Embedded Python:** true
**Pytorch Version:** 2.8.0+cu129
**Arguments:** ComfyUI\main.py
**RAM Total:** 31.11 GB
**RAM Free:** 21.6 GB
**Devices**
**Name** cuda:0 NVIDIA GeForce RTX 4090 : cudaMallocAsync
**Type:** cuda
**VRAM Total:** 23.99 GB
**VRAM Free:** 22.45 GB
**Torch VRAM Total:** 0 B
**Torch VRAM Free:** 0 B

**Terminal Output:**
got prompt
Requested to load WanTEModel
loaded completely 19986.588032531738 6419.477203369141 True
Using scaled fp8: fp8 matrix mult: True, scale input: True
model weight dtype torch.float16, manual cast: None
model_type FLOW
Requested to load WAN21
loaded completely 15268.594980926515 13629.075424194336 True
0%| | 0/2 [00:00...
comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.APPLY_MODEL, transformer_options)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
).execute(x, t, c_concat, c_crossattn, control, transformer_options, **kwargs)
~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Y:\ComfyUI\ComfyUI\comfy\patcher_extension.py", line 111, in execute
return self.original(*args, **kwargs)
~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "Y:\ComfyUI\ComfyUI\comfy\model_base.py", line 194, in _apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Y:\ComfyUI\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1773, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "Y:\ComfyUI\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1784, in _call_impl
return forward_call(*args, **kwargs)
File "Y:\ComfyUI\ComfyUI\comfy\ldm\wan\model.py", line 599, in forward
return self.forward_orig(x, timestep, context, clip_fea=clip_fea, freqs=freqs, transformer_options=transformer_options, **kwargs)[:, :, :t, :h, :w]
~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Y:\ComfyUI\ComfyUI\comfy\ldm\wan\model.py", line 525, in forward_orig
x = self.patch_embedding(x.float()).to(x.dtype)
~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^
File "Y:\ComfyUI\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1773, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "Y:\ComfyUI\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1784, in _call_impl
return forward_call(*args, **kwargs)
File "Y:\ComfyUI\ComfyUI\comfy\ops.py", line 149, in forward
return self.forward_comfy_cast_weights(*args, **kwargs)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "Y:\ComfyUI\ComfyUI\comfy\ops.py", line 145, in forward_comfy_cast_weights
return self._conv_forward(input, weight, bias)
~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^
File "Y:\ComfyUI\python_embeded\Lib\site-packages\torch\nn\modules\conv.py", line 712, in _conv_forward
return F.conv3d(
~~~~~~~~^
input, weight, bias, self.stride, self.padding, self.dilation, self.groups
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
**RuntimeError: Given groups=1, weight of size [5120, 36, 1, 2, 2], expected input[1, 64, 21, 80, 80] to have 36 channels, but got 64 channels instead**

Prompt executed in 77.74 seconds

[video_wan2_2_14B_t2v.json](https://github.com/user-attachments/files/21776205/video_wan2_2_14B_t2v.json)