TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

45874dc8-8936-4a62-8e68-e4fa45ed57ac

Queued
Jul 29, 2026, 10:21 AM
Completed
Jul 29, 2026, 10:21 AM
Execution time
6.9s
Outputs
1 · 1.4 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00586_.png

node 3 · 1.4 MB

Text prompts

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

Lucy, Receptionist; types at her computer; mentions another driver., Projects an efficient and professional demeanor. Her hands are poised for typing. Wears natural-looking makeup.

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.