使用 CogVideoX-Fun-V1.1-5b-control 推理时失败

你好，当我使用CogVideoX-Fun-V1.1-5b-control 模型进行 predict_v2v_control.py 推理时候报错：
RuntimeError: mat1 and mat2 shapes cannot be multiplied (3456x256 and 264x3072)
报错发生在 cogvideox/models/transformer3d.py", line 147 image_embeds = self.proj(image_embeds) 这句
请问这个是代码不支持V1.1-5b-control模型吗

具体报错信息如下：
Traceback (most recent call last):
File "/seaweedfs/training/experiments/zaiyou/envs/torch2.5.1/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/seaweedfs/training/experiments/zaiyou/envs/torch2.5.1/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/root/.vscode-server/extensions/ms-python.debugpy-2025.0.0/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/main.py", line 71, in
cli.main()
File "/root/.vscode-server/extensions/ms-python.debugpy-2025.0.0/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 501, in main
run()
File "/root/.vscode-server/extensions/ms-python.debugpy-2025.0.0/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 351, in run_file
runpy.run_path(target, run_name="main")
File "/root/.vscode-server/extensions/ms-python.debugpy-2025.0.0/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 310, in run_path
return _run_module_code(code, init_globals, run_name, pkg_name=pkg_name, script_name=fname)
File "/root/.vscode-server/extensions/ms-python.debugpy-2025.0.0/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 127, in _run_module_code
_run_code(code, mod_globals, init_globals, mod_name, mod_spec, pkg_name, script_name)
File "/root/.vscode-server/extensions/ms-python.debugpy-2025.0.0/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 118, in _run_code
exec(code, run_globals)
File "/seaweedfs/training/experiments/zaiyou/eeds_code/ComfyUI/custom_nodes/CogVideoX-Fun/predict_v2v_control.py", line 138, in
sample = pipeline(
File "/seaweedfs/training/experiments/zaiyou/envs/torch2.5.1/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/seaweedfs/training/experiments/zaiyou/eeds_code/ComfyUI/custom_nodes/CogVideoX-Fun/cogvideox/pipeline/pipeline_cogvideox_control.py", line 906, in call
noise_pred = self.transformer(
File "/seaweedfs/training/experiments/zaiyou/envs/torch2.5.1/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/seaweedfs/training/experiments/zaiyou/envs/torch2.5.1/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "/seaweedfs/training/experiments/zaiyou/envs/torch2.5.1/lib/python3.10/site-packages/accelerate/hooks.py", line 170, in new_forward
output = module._old_forward(*args, **kwargs)
File "/seaweedfs/training/experiments/zaiyou/eeds_code/ComfyUI/custom_nodes/CogVideoX-Fun/cogvideox/models/transformer3d.py", line 589, in forward
hidden_states = self.patch_embed(encoder_hidden_states, hidden_states)
File "/seaweedfs/training/experiments/zaiyou/envs/torch2.5.1/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/seaweedfs/training/experiments/zaiyou/envs/torch2.5.1/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "/seaweedfs/training/experiments/zaiyou/eeds_code/ComfyUI/custom_nodes/CogVideoX-Fun/cogvideox/models/transformer3d.py", line 147, in forward
image_embeds = self.proj(image_embeds)
File "/seaweedfs/training/experiments/zaiyou/envs/torch2.5.1/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/seaweedfs/training/experiments/zaiyou/envs/torch2.5.1/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "/seaweedfs/training/experiments/zaiyou/envs/torch2.5.1/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 125, in forward
return F.linear(input, self.weight, self.bias)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (3456x256 and 264x3072)

Reproduce the failure through predict_v2v_control.py, then inspect cogvideox/models/transformer3d.py at line 147 and the control pipeline entry point in pipeline_cogvideox_control.py. Compare the image embedding dimensions from CogVideoX-Fun-V1.1-5b-control with the projection layer configuration. Done means establishing compatible inference or documenting that this model is unsupported with the current code.