Closed axior closed 1 week ago
That is a bug. Cause of the issue is that AutoAdjust
node output is set to RGBA mode, it has been fixed now. But note that if the input image is RGBA, then will still be output to RGBA. At this time, if the subsequent node does not support such format, please convert it to RGB first. You can use ImageRemoveAlpha
node to implement it.
That is a bug. Cause of the issue is that
AutoAdjust
node output is set to RGBA mode, it has been fixed now. But note that if the input image is RGBA, then will still be output to RGBA. At this time, if the subsequent node does not support such format, please convert it to RGB first. You can useImageRemoveAlpha
node to implement it.
Thank you!! Damn of course it's alpha, don't know why I didn't think of this, it also happened in the past and I figured it out, I'm getting old..
Hello, I am testing your AutoAdjust node and it somehow breaks the comfyui workflow, it works well if attaching the node to a previewer or save node, but when I link it to another part of the workflow (image batch or depthanything for example) it gives an error, this is the error I got for image batch: Sizes of tensors must match except in dimension 0. Expected size 4 but got size 3 for tensor number 1 in the list.
File "D:\AI\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-0246\utils.py", line 381, in new_func
res_value = old_func(*final_args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\masquerade-nodes-comfyui\MaskNodes.py", line 1124, in append
result = torch.cat((result, image2), 0)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
I have tried with other nodes from LayerStyle and those work without any issues.
Here is a screenshot recreating the issue with Depth Anything