TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

80ecb328-2e99-4c72-9bca-6d3962cb9c8c

Queued
Jul 26, 2026, 12:45 AM
Completed
Jul 26, 2026, 12:45 AM
Execution time
8.2s
Outputs
1 · 1.6 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00440_.png

node 3 · 1.6 MB

Text prompts

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

Elena's Study, A small, intimate study with dark mahogany wood paneling and packed bookshelves lining the walls. A worn leather armchair sits beside a heavy wooden desk, both casting deep shadows. A single, ornate brass desk lamp casts a focused, warm amber glow onto a scattering of old books and papers, sharply contrasting with the gloomy, rain-streaked window looking out into a dark, blurry night., The room is filled with the subtle scent of aged paper and polished wood. The steady pitter-patter of rain against the windowpane provides a constant, soothing auditory backdrop. Where visible between the bookshelves, the wallpaper features a subtle, deep green damask pattern. A half-empty cup of herbal tea rests on a coaster next to the lamp. The atmosphere evokes quiet contemplation and a sense of cozy refuge from the storm outside.

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.