TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

4dd47b33-3026-4a9d-9405-4b399dafcbb7

Queued
Jul 27, 2026, 09:57 AM
Completed
Jul 27, 2026, 09:57 AM
Execution time
6.4s
Outputs
1 · 1.6 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00494_.png

node 3 · 1.6 MB

Text prompts

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

book, A medium-sized, hardcover book with a deep crimson-red faux-leather cover, its spine showing faint, unreadable gold-embossed lettering. Resting neatly on its closed front cover are a pair of classic, slender gold-toned wire-frame reading glasses, folded shut., The book measures approximately 6x9 inches, with slight scuffing visible on the edges of its cover, indicating gentle use. Its pages are an aged cream color, slightly yellowed at the edges. The reading glasses have oval lenses and are positioned with their temples lying flat across the book's surface, just above the center, suggesting a recent interruption. The gold-toned frames gleam faintly under ambient light.

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.