TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

cef11645-aa9f-4caf-8f9a-c28554a47dca

Queued
Jul 27, 2026, 09:56 AM
Completed
Jul 27, 2026, 09:56 AM
Execution time
9.9s
Outputs
1 · 1.5 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00493_.png

node 3 · 1.5 MB

Text prompts

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

reading glasses, A pair of reading glasses, folded neatly and resting on an open, well-worn book., The glasses feature slim, rectangular frames made of polished dark tortoiseshell acetate with slender antique gold metal temples. Their lenses are clean and slightly magnifying. They are folded precisely and placed on the binding of a medium-sized hardcover book. The book has a muted, forest green cloth cover, a slightly faded gold title on the spine, and is open face-down, indicating a pause in reading. The entire arrangement suggests a quiet, intellectual space under soft, 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.