TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

b89cb0ee-7482-4ccd-99fc-fe18c16817d8

Queued
Jul 26, 2026, 01:09 AM
Completed
Jul 26, 2026, 01:09 AM
Execution time
8.5s
Outputs
1 · 1.2 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00443_.png

node 3 · 1.2 MB

Text prompts

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

A moody and intimate medium close-up of Elena Voss @char_0d9e22bc1cc140a99fc9f612dcc5285d in Elena's Study @loc_0268a2ca06e64e6d9f0ef325aada11b3. Her expression is deeply pensive, her gaze lost in the unseen darkness beyond the frame. A single warm lamp @prop_fe85a7a7b92c4b6d9cea7d7d01ead91e, positioned just outside the frame to the right, casts a soft, directional low-key light, illuminating one side of her face and creating deep, dramatic shadows on the other, reminiscent of Hollywood noir. The long lens creates a compressed, intimate feel with a very shallow depth of field, blurring the dark background into an abstract blend of cool greys and deep blues. Colors are rich but desaturated, emphasizing the warm glow against the cool shadows. The overall mood is one of profound thought and quiet contemplation.

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.