e22d1c44-4a3b-4ddd-bb31-b52a9c1be8d7
- Queued
- Jul 18, 2026, 01:54 PM
- Completed
- Jul 18, 2026, 01:55 PM
- Execution time
- 31.5s
- Outputs
- 0 · 0 B
- Inputs
- 2
- Cached nodes
- —
Failure
Failed to generate video: No video was generated. This may be due to content safety filters.
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 225, in generate_video
raise RuntimeError(f"Failed to generate video: {str(e)}")
Outputs
0The run failed before producing any output.
Text prompts
1MCU @Vivienne alone at the doorway threshold. The final shot. First second: from the start frame — mouth shaping the "D" — she speaks his name: "Daniel?" Delivery: barely above a whisper. One word. Her voice catches on the second syllable — a micro-crack, involuntary, the sound of someone saying a name they haven't said in a long time. Her eyes stay locked on off-camera @Daniel. The word comes out as a question — rising inflection, disbelief still present. She is asking if he is real. 1.5 to 2.5s: a breath. She inhales — a deeper breath than any in the sequence, visible chest rise. Her eyes search his off-camera face. Then she speaks again: "How are you here?" Delivery: quiet, measured, each word separate, as if she is constructing the sentence while speaking it. "How" is soft. "Are you" runs together. "Here" lands with weight — a full stop, not a question, despite the words. Her head tilts by two degrees to her left. Her glistening eyes hold. 3.0 to 4.0s: silence after the line. Her mouth closes. Her chin dips by one degree. She blinks — slow, a full 0.5-second blink, the kind that resets a person. When her eyes reopen they are calmer. The surprise has settled. What remains is something private and unresolvable in this frame. 4.0 to 5.0s: HOLD. She is still. Eyes on him. The escaped auburn strands sway with the train's gentle movement. The warm golden light holds on her face. One more small breath. Then nothing. CUT TO BLACK. Camera: very slow 2% push-in through the entire shot, settling motionless at 4.0s. By the end her face fills the frame even tighter. Focus locked on her eyes. Real time. Her voice is the last sound. Then silence. Then black.
Input media
2Source images and video this run consumed.
