TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

923328b0-dc6e-449f-aab0-ea937aecb13e

Queued
Jul 29, 2026, 10:24 AM
Completed
Jul 29, 2026, 10:24 AM
Execution time
7.4s
Outputs
1 · 1.4 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00594_.png

node 3 · 1.4 MB

Text prompts

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

package, A small, plain cardboard shipping box, initially presented as empty, but later an identical box is revealed to contain a presentation clicker., This prop consists of two identical, small rectangular cardboard boxes. Each box measures approximately 8 inches (L) x 4 inches (W) x 2 inches (H) (20cm x 10cm x 5cm). They are constructed from plain, unbleached kraft brown corrugated cardboard with a matte finish. The boxes feature standard tuck-top and snap-bottom closures, allowing them to be opened and re-sealed without noticeable damage. They are clean and free of any labels, markings, or excessive wear, ensuring they appear indistinguishable. The empty box should feel noticeably light, while the identical second box, containing the presentation clicker, should have a slight but consistent weight.

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.