TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

7033d840-157a-4f1f-9f2c-1cf7eedfa745

Queued
Jul 27, 2026, 12:32 PM
Completed
Jul 27, 2026, 12:32 PM
Execution time
17.8s
Outputs
1 · 5.2 MB
Inputs
2
Cached nodes
3

Outputs

1

Click an image to view it full size.

character_ref_00512_.png

node 3 · 5.2 MB

Text prompts

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

Low table-level insert at the dresser: the oak top drawer sliding open, @Maya's hand on the handle, folded clothes and warm lamp glow raking across the wood grain. 47mm, T2.8. (Start frame for: drawer slides open.) + REALISM + LIGHT + 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_00511_.png

node 4 · 5.6 MB

character_ref_00499_.png

node 6 · 5.9 MB