TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

8f75c717-11e9-4e82-aa36-82ac9b114d45

Queued
Jul 27, 2026, 12:24 PM
Completed
Jul 27, 2026, 12:25 PM
Execution time
20.0s
Outputs
1 · 7.5 MB
Inputs
2
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00508_.png

node 3 · 7.5 MB

Text prompts

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

Plate: an old printed 4×6 photograph, slightly faded with age wear on the paper — @Maya and @Dev younger-feeling and genuinely happy, standing close outside the front of a modest house neither is familiar with, daylight in the photo. Faces clearly theirs. + REALISM + STYLE

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

2

Source images and video this run consumed.

character_ref_00497_.png

node 4 · 5.8 MB

character_ref_00498_.png

node 6 · 5.9 MB