TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

6803130c-cee6-4109-bc6d-042e3d3c6f2f

Queued
Jul 27, 2026, 09:11 PM
Completed
Jul 27, 2026, 09:11 PM
Execution time
6.7s
Outputs
1 · 1.5 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00573_.png

node 3 · 1.5 MB

Text prompts

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

Backpack, A medium-sized, utilitarian backpack, constructed from durable charcoal grey canvas with robust black nylon straps and silver metal buckles, cinched tightly to Maize's back as she prepares to depart at dawn., The backpack features a main compartment with a drawstring closure, covered by a top flap secured by two adjustable black nylon straps with quick-release buckles. Two smaller side pockets and a larger front zippered pocket provide additional storage. The charcoal canvas shows slight fading and minor scuffs consistent with frequent use, but all straps and buckles appear sturdy and fully functional. It sits high and snug on Maize's back, with the adjustable shoulder, chest, and hip straps pulled taut, suggesting a heavy but well-distributed load.

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.