TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

40588964-6a35-4394-aa9f-acb159055c2a

Queued
Jul 27, 2026, 06:07 AM
Completed
Jul 27, 2026, 06:08 AM
Execution time
6.9s
Outputs
1 · 1.7 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00469_.png

node 3 · 1.7 MB

Text prompts

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

departures board, A digital display board, reminiscent of older segmented LED types, that flickers as it updates, presenting real-time train departure information., A large, rectangular information display, approximately 2 meters wide and 1.5 meters tall, encased in dark charcoal grey, brushed metal. The screen is a segmented LED type, displaying glowing amber text against a dark background. The numbers and letters appear to be composed of individual glowing dots or segments. The board exhibits a noticeable, intermittent flickering effect, particularly when information updates, where segments briefly dim or pixels momentarily glitch before resolving. It's wall-mounted, positioned to be easily visible, with a slight accumulation of dust in crevices and minor scuffs on the casing from years of public use. Currently, it predominantly displays departure times and platform numbers, with '00:04' prominently featured and shimmering as it updates.

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

0

This run had no input media — it generated from prompts alone.