This response is not simple text.Use the result.parts accessor or the full result.candidates[index].content.parts lookup instead.

[whmc76]

ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "E:\IMAGE\ComfyUI_windows_portable\ComfyUI\execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_windows_portable\ComfyUI\execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_windows_portable\ComfyUI\execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Gemini\GeminiAPINode.py", line 92, in generate_content
textoutput = response.text
^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_windows_portable\python_embeded\Lib\site-packages\google\generativeai\types\generation_types.py", line 328, in text
raise ValueError(
ValueError: The response.text quick accessor only works for simple (single-Part) text responses. This response is not simple text.Use the result.parts accessor or the full result.candidates[index].content.parts lookup instead.

[jags111]

I am having same issue and any recommendations for same. Please advise.. or is some thing changed in the workflow when using the text prompt outputs

[whmc76]

Maybe it's because of the long input? I reduced the length of the input text and it can be used, but I still want to be unrestricted, after all, it seems that the api supports it.

I am having same issue and any recommendations for same. Please advise.. or is some thing changed in the workflow when using the text prompt outputs

[jags111]

got it to work with changed input params or prompts

[OliverCrosby]

What did you have to change?

I wonder if the error is because sometimes gemini thinks you're asking it to generate an image, which it would do instead of returning with text.