TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

f2234cde-bd5f-4066-b900-68709715a705

Queued
Aug 29, 2026, 04:26 PM
Completed
Aug 29, 2026, 04:26 PM
Execution time
10.4s
Outputs
1 · 1.4 MB
Inputs
2
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00771_.png

node 3 · 1.4 MB

Text prompts

4
Promptnode 1 · PrimitiveStringMultiline · valueCharacter Description (your input)

i want a 4k image of this man and the background should be grey and he should be looking into the camera with neutral expression

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.

2 other text fields— sigmas, filenames, and other non-prompt strings the logger swept up

node 4 · LoadImage · image

WhatsApp Image 2026-08-29 at 9.38.39 PM.jpeg

node 5 · LoadImage · image

WhatsApp Image 2026-08-29 at 9.41.49 PM.jpeg

Input media

2

Source images and video this run consumed.

WhatsApp Image 2026-08-29 at 9.38.39 PM.jpeg

node 4 · 71 KB

WhatsApp Image 2026-08-29 at 9.41.49 PM.jpeg

node 5 · 94 KB