TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

01be120f-04b2-4235-9ef5-2ea0b4a3bc22

Queued
Jul 17, 2026, 03:05 PM
Completed
Jul 17, 2026, 03:05 PM
Execution time
9.1s
Outputs
1 · 1.8 MB
Inputs
1
Cached nodes
1

Outputs

1

Click an image to view it full size.

character_ref_00282_.png

node 3 · 1.8 MB

Text prompts

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

3. Overlay the reference face with high-contrast digital static and perlin noise textures. The noise should be dense enough to break the continuous surface of the skin but sparse enough to see the eyes and mouth positions. Technical glitch aesthetic.

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