TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

e9d55afe-1f1d-48e3-b0ce-185197ff502d

Queued
Jul 17, 2026, 03:04 PM
Completed
Jul 17, 2026, 03:04 PM
Execution time
10.4s
Outputs
1 · 1.4 MB
Inputs
1
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00281_.png

node 3 · 1.4 MB

Text prompts

3
Promptnode 1 · PrimitiveStringMultiline · valueCharacter Description (your input)

2. A high-fidelity digital human asset. Overlay a faint, translucent blue geometric wireframe mesh onto the face. The mesh lines should follow the contours of the cheeks and forehead. The eyes and mouth must remain clear. Rendered in a technical software interface 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.

1 other text field— sigmas, filenames, and other non-prompt strings the logger swept up

node 4 · LoadImage · image

character_ref_00274_ (1).png

Input media

1

Source images and video this run consumed.

character_ref_00274_ (1).png

node 4 · 1.3 MB