This is a new error. I can no longer select a portion of the image to inpaint. I can only generate the whole image. Occurrs when I try to replace background, inpaint a selection, expand image, etc... any time I'm not re-generating the entire image.
ROCm (linux) or ZLUDA (windows) gives same errors. DirectML (windows) just crashes with no error.
!!! Exception during processing !!! InpaintModelConditioning.encode() missing 1 required positional argument: 'noise_mask'
Traceback (most recent call last):
File "/home/ricperry1/ComfyUI/execution.py", line 323, 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 "/home/ricperry1/ComfyUI/execution.py", line 198, 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 "/home/ricperry1/ComfyUI/execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)
File "/home/ricperry1/ComfyUI/execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ricperry1/ComfyUI/custom_nodes/comfyui-inpaint-nodes/nodes.py", line 216, in encode
positive, negative, latent = nodes.InpaintModelConditioning().encode(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: InpaintModelConditioning.encode() missing 1 required positional argument: 'noise_mask'
Prompt executed in 0.01 seconds
This is a new error. I can no longer select a portion of the image to inpaint. I can only generate the whole image. Occurrs when I try to replace background, inpaint a selection, expand image, etc... any time I'm not re-generating the entire image.
ROCm (linux) or ZLUDA (windows) gives same errors. DirectML (windows) just crashes with no error.