TokiToki Internal
Atlas + S3
All runs
ErrorComfyUI

ac411da2-5fe5-4bb3-87f4-505e5efc6cd8

Queued
Jul 20, 2026, 04:08 PM
Completed
Jul 20, 2026, 04:08 PM
Execution time
6 ms
Outputs
0 · 0 B
Inputs
1
Cached nodes
2

Failure

RuntimeErrorin GeminiImageDirect (node 2)

No Gemini API key found. Put it in the node's api_key field, or set GEMINI_API_KEY / GOOGLE_API_KEY, or create /home/ec2-user/ComfyUI/custom_nodes/ComfyUI-GeminiDirect/api_key.txt with your key on one line.

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-GeminiDirect/__init__.py", line 136, in generate
    key = _resolve_key(api_key)
          ^^^^^^^^^^^^^^^^^^^^^
  File "/home/ec2-user/ComfyUI/custom_nodes/ComfyUI-GeminiDirect/__init__.py", line 51, in _resolve_key
    raise RuntimeError(

Outputs

0

The run failed before producing any output.

Text prompts

2
Promptnode 1 · PrimitiveStringMultiline · valueCharacter Description (your input)

Casting portrait, neutral grey seamless background, soft even overcast-window key with a gentle 3:1 ratio, medium close-up plus a 3/4 profile. A woman who appears 28 years old, of ambiguous European heritage — she reads as someone who has lived far longer than her face admits, a stillness in her that is almost unsettling. Face geometry: oval face, high but soft cheekbones, a straight nose with a slightly rounded tip, a naturally serious resting mouth with a faint downturn. Eyes: grey-green, deep-set, heavy upper lids that give her a watchful, tired quality — the most important feature, they must look like they are always calculating something behind them. Eyebrows natural, softly arched, slightly uneven. Skin: fair with cool undertones, absolutely unretouched — visible pores across the cheeks and nose, faint natural under-eye shadow, a few tiny freckles on the left cheekbone, the faintest fine lines at the outer eyes. A small pale scar just below the collarbone edge, barely visible. Hair: dark ash-brown, shoulder length, straight with a natural slight wave, centre part, a few loose flyaway strands, matte not glossy — real hair, not salon hair. Build: slim, average height, understated. No makeup, or the invisible suggestion of none. The grounded, interior intensity of a serious young character actor — presence without performance. Natural expression at rest, lips closed, looking directly to camera then away. Shot on a full-frame mirrorless camera, 50mm lens at f4 for full facial sharpness, flat overcast daylight from a large north window camera-left, no fill bounce, no artificial light, no color grade. Hyperrealistic photograph, skin texture fully preserved, documentary realism, absolutely no beauty retouching. 9:16 vertical. Negatives: beauty filter, smooth skin, plastic skin, waxy, airbrushed, makeup glam, studio glamour lighting, cinematic teal-orange, color grade, HDR, oversaturated, model posing, symmetrical perfect face, CGI, 3D render, anime

Systemnode 2 · GeminiImageDirect · system_promptCharacter Image Generator (Nano Banana)

Generate a single, hyper-realistic character reference image (strictly no collages, text, watermarks, or borders). The image must feature a cinematic, three-quarter portrait of the described character, maintaining a sharp, tack-focused emphasis on the face with natural skin textures, pore details, and realistic micro-expressions. The lighting should be cinematic and directional (e.g., subtle split or Rembrandt lighting) to give depth, blending seamlessly with the environment specified in the character description. The character must have a natural, living presence, looking slightly off-camera or directly at the lens with a subtle, context-aware expression. Ensure the full head, neck, and upper shoulders are completely unobstructed. This image serves as a high-fidelity identity blueprint for temporal-consistent video generation.

Input media

1

Source images and video this run consumed.

No preview

white_bg.jfif

node 4 · 4.4 KB