TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

f6f8af1c-638b-4f48-b881-6dd2081b50c9

Queued
Jul 27, 2026, 12:33 PM
Completed
Jul 27, 2026, 12:33 PM
Execution time
6.7s
Outputs
1 · 1.6 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00515_.png

node 3 · 1.6 MB

Text prompts

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

Bookshelves, A tall, sturdy wooden bookshelf, approximately 200cm high, made from dark, polished oak. It features five fixed shelves, each about 3cm thick, designed to hold heavy books without bowing. The overall design is traditional, with a simple crown molding at the top and a plinth base., The bookshelf has a rich mahogany stain with a semi-gloss lacquer finish, which highlights the natural grain of the wood. The solid wood construction includes visible, sturdy joinery. Each shelf provides approximately 35cm of vertical space. The backing is a solid wood panel. Minor scuffs and wear are visible on the lower shelves and edges, indicating consistent use over time. It reflects ambient light with a warm, subdued glow.

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.