TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

bba058ee-ec9e-4a73-a2ae-41ddf0bd828a

Queued
Jul 26, 2026, 01:19 AM
Completed
Jul 26, 2026, 01:19 AM
Execution time
7.6s
Outputs
1 · 1.3 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00444_.png

node 3 · 1.3 MB

Text prompts

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

Medium close-up of Elena Voss @char_0d9e22bc1cc140a99fc9f612dcc5285d in her study @loc_0268a7a7b92c4b6d9cea7d7d01ead91e. She sits, lost in thought, her gaze slightly downward. A single warm lamp @prop_fe85a7a7b92c4b6d9cea7d7d01ead91e on a nearby desk casts a soft, directional glow from the left, highlighting one side of her face and leaving the other in deep, moody shadow. The background is softly blurred. Pensive, intimate atmosphere with a dramatic lighting contrast. Shot on an 85mm lens, rich, desaturated color palette with warm accents.

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.