To begin with, the project is simply a one-second movement of a character without a background, which I created to test the rendering functionality.
Procedure followed:
- Launching the server (
AI Render Setting – Launch): 
OK
- Then I went to the video rendering section (video render icon – Workflows section). I tested several styles: Films Video Style, 2D Anime Video Style, and others. For this case, I chose Films Video Style.
- Preview launch: OK. The preview runs without any issues. When I check the folder, I find the following files:
RenderImage.png
RenderImageDepth.png
RenderImageNormal.png
RenderImageOpenPose.png
RenderVideo.mp4
RenderVideoDepth.mp4
RenderVideoNormal.mp4
RenderVideoOpenPose.mp4
Result0.png
Setting.json
Workflow_Pre.json
So I have the results, and everything seems fine.
Video render launch:
I tested with: "Wan2.1 fun 1.3B Control" and also "Wan Vace 1.3b" — both returned the same error message. I’ll illustrate using "Wan2.1 fun 1.3B Control".
I click on Render, then Confirm, and confirm the filename to be generated. That’s when the following error occurs. Below is the part I copied from the console, which I believe relates to the error message:
"..Requested to load WanVAE
0 models unloaded.
loaded partially 128.0 127.9998779296875 0
0 models unloaded.
loaded partially 128.0 127.9998779296875 0
!!! Exception during processing !!! ‘UNetModel’ object has no attribute ‘blocks’
Traceback (most recent call last):
File “C:\Program Files\Common Files\Reallusion\RL_ComfyUI\ComfyUI\execution.py”, line 349, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “C:\Program Files\Common Files\Reallusion\RL_ComfyUI\ComfyUI\execution.py”, line 224, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “C:\Program Files\Common Files\Reallusion\RL_ComfyUI\ComfyUI\execution.py”, line 196, in _map_node_over_list
process_inputs(input_dict, i)
File “C:\Program Files\Common Files\Reallusion\RL_ComfyUI\ComfyUI\execution.py”, line 185, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “C:\Program Files\Common Files\Reallusion\RL_ComfyUI\ComfyUI\custom_nodes\ComfyUI-KJNodes\nodes\model_optimization_nodes.py”, line 1574, in enhance
for idx, block in enumerate(diffusion_model.blocks):
^^^^^^^^^^^^^^^^^^^^^^
File “C:\Program Files\Common Files\Reallusion\RL_ComfyUI\python_embeded\Lib\site-packages\torch\nn\modules\module.py”, line 1940, in getattr
raise AttributeError(
AttributeError: ‘UNetModel’ object has no attribute ‘blocks’
Prompt executed in 22.49 seconds".
After launching this render, the following files were added:
Workflow_Gen.json
gen_setting
So I go to the ComfyUI interface:
- Render Setting → Open WebUI
- I open the workflow: Workflow → Open → History folder → Select workflow: Workflow_Gen.json
- I run the workflow: Run
And then I get this error message:
WanVideoEnhanceAVideoKJ
'UNetModel' object has no attribute 'blocks'
With the 2D render, I received this error:
KSampler
mat1 and mat2 shapes cannot be multiplied (77x768 and 4096x5120)
I suspect this may be related to model compatibility or how the models are combined.
Due to poor internet connectivity, I manually downloaded the models by searching for the appropriate links and placing them in the correct folders. If possible, please provide the correct model links so I can re-download and place them properly.
Otherwise, I’m open to your guidance on what’s going wrong and what steps I should take to resolve it.
