Add support For SeedVR2

[yousef-rafat]

[Kosinkadink]

Currently, trying either image or video inputs results in this error during VAE Decode:

!!! Exception during processing !!! Given groups=1, weight of size [512, 16, 3, 3, 3], expected input[1, 1, 16, 3, 332] to have 16 channels, but got 1 channels instead
Traceback (most recent call last):
  File "/home/kosin/ComfyUI/execution.py", line 516, 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 "/home/kosin/ComfyUI/execution.py", line 330, 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 "/home/kosin/ComfyUI/execution.py", line 304, in _async_map_node_over_list
    await process_inputs(input_dict, i)
  File "/home/kosin/ComfyUI/execution.py", line 292, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^
  File "/home/kosin/ComfyUI/nodes.py", line 298, in decode
    images = vae.decode(samples["samples"])
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/custom_nodes/benchmark/__init__.py", line 307, in wrapper_VAE_decode
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/comfy/sd.py", line 799, in decode
    out = self.process_output(self.first_stage_model.decode(samples, **vae_options).to(self.output_device).float())
                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/comfy/ldm/seedvr/vae.py", line 1564, in decode
    x = super().decode(latent).squeeze(2)
        ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/comfy/ldm/seedvr/vae.py", line 1455, in decode
    decoded = self.slicing_decode(z)
              ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/comfy/ldm/seedvr/vae.py", line 1486, in slicing_decode
    return self._decode(z)
           ^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/comfy/ldm/seedvr/vae.py", line 1479, in _decode
    output = self.decoder(latent)
             ^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/comfy/ldm/seedvr/vae.py", line 1290, in forward
    sample = self.conv_in(sample)
             ^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/comfy/ldm/seedvr/vae.py", line 386, in forward
    return super().forward(input)
           ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/venv/lib/python3.12/site-packages/torch/nn/modules/conv.py", line 717, in forward
    return self._conv_forward(input, self.weight, self.bias)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/kosin/ComfyUI/venv/lib/python3.12/site-packages/torch/nn/modules/conv.py", line 712, in _conv_forward
    return F.conv3d(
           ^^^^^^^^^
RuntimeError: Given groups=1, weight of size [512, 16, 3, 3, 3], expected input[1, 1, 16, 3, 332] to have 16 channels, but got 1 channels instead