TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

363e6f91-714b-455a-b6a6-55df848750b3

Queued
Jul 27, 2026, 09:56 AM
Completed
Jul 27, 2026, 09:56 AM
Execution time
7.0s
Outputs
1 · 1.6 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00492_.png

node 3 · 1.6 MB

Text prompts

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

photos, A curated collection of framed photographs and a photo album, depicting cherished memories and personal history, displayed throughout Meera's living room., The collection includes approximately 8-10 individual photos. On a polished dark wood side table, there are three varying-sized photos in antique silver-plated frames, showing Meera with a younger man (likely a son) and a smiling older woman. One large 8x10 inch photo hangs on the wall near the armchair, framed in a simple, elegant dark walnut wood, depicting a vibrant landscape from a past trip. On the coffee table, a slightly worn, deep burgundy leather photo album lies open, displaying several sepia-toned candid shots of family gatherings from years past. The photos vary in age, some appearing modern and crisp, others with a soft, faded quality, consistent with older prints. The overall aesthetic is one of warmth and personal history, reflecting a life well-lived.

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.