ErrorComfyUI

5b0397d1-8c45-4cd1-933d-b0c042c1de1a

Queued: Jul 20, 2026, 04:30 PM
Completed: Jul 20, 2026, 04:30 PM
Execution time: 14 ms
Outputs: 0 · 0 B
Inputs: 2
Cached nodes: 1

Failure

ValueErrorin JMGeminiVideoGenerator (node 1)

No Gemini API key found. Leave the node's api_key blank AND set GEMINI_API_KEY in /etc/comfyui.env, or paste a key into the node.

Stack trace

  File "/home/ec2-user/ComfyUI/execution.py", line 542, in execute
    output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/execution.py", line 341, in get_output_data
    return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/execution.py", line 315, in _async_map_node_over_list
    await process_inputs(input_dict, i)
  File "/home/ec2-user/ComfyUI/execution.py", line 303, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/custom_nodes/ComfyUI-JM-Gemini-API/nodes/jm_gemini_video_node.py", line 163, in generate_video
    gemini_api_key = _resolve_api_key(gemini_api_key)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/custom_nodes/ComfyUI-JM-Gemini-API/nodes/jm_gemini_video_node.py", line 39, in _resolve_api_key
    raise ValueError(

Outputs

The run failed before producing any output.

Text prompts

Promptnode 1 · JMGeminiVideoGenerator · prompt“JM Gemini Video Generator”

MCU @Marcus explaining the operational logic: "The train splits at Kansas City. Front four cars continue to Los Angeles. The rest go south to San Diego. If you don't know which city she's headed to, we're searching blind." Delivery: patient professional baritone, the cadence of a man explaining something obvious to someone who should know better. Not condescending — informational. Pace approximately 3 words per second. Weight on "Los Angeles" and "San Diego" — he says the city names clearly, as destinations. Small pause after "Kansas City" to let the geography land. Eyes on off-camera @Daniel throughout. His right hand lifts @LedgerBook slightly and tilts it as a visual aid — a gestural habit, pointing vaguely forward with the book to indicate the front of the train. Final beat: "searching blind" lands flat and level. Mouth closes. One brow lifts a fraction — the ball is in @Daniel's court. Camera: locked, organic micro-drift. 50mm. Focus on eyes. Badge legible. Warm key constant. Cap gold cord holds highlight. Real time, operational patience.

Input media

Source images and video this run consumed.

character_ref_00297_.png
node 5 · 1.4 MB