TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

dddd0672-233e-42cd-babf-2fcc3dd19545

Queued
Jul 27, 2026, 12:34 PM
Completed
Jul 27, 2026, 12:34 PM
Execution time
6.9s
Outputs
1 · 1.5 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00519_.png

node 3 · 1.5 MB

Text prompts

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

old laptop, A thick, boxy, matte dark grey plastic laptop, dating from the late 1990s or early 2000s. Its robust form features prominent cooling vents and a side-mounted optical drive. The laptop appears well-used, with a slightly faded, full-sized keyboard and numerous minor scuffs on its casing. When Meera opens it, the small, low-resolution LCD screen flickers to life, presenting a bright blue password input prompt against a dark background, indicating it's locked., The laptop's lid closes with a solid click, and its hinges feel stiff but secure. A faint, continuous whirring of an internal fan is audible when powered on, accompanied by a soft amber LED indicator near the power button. Visible ports on its sides include a VGA output, two USB-A ports, and an Ethernet jack, all consistent with older technology. The overall impression is of a once-reliable but now outdated piece of equipment, heavy and functional despite its age.

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.