TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

4447891b-a32f-4d04-8386-416d239419cf

Queued
Jul 22, 2026, 03:22 PM
Completed
Jul 22, 2026, 03:22 PM
Execution time
11.7s
Outputs
1 · 1.4 MB
Inputs
3
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00360_.png

node 3 · 1.4 MB

Text prompts

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

[REFS: attach @Elena and @Aidan face refs] Medium wide shot of both people sitting on the weathered porch steps facing each other. The woman in the oatmeal sweater sits upper-left on the higher step, knees drawn up, arms around them. The man in the navy henley sits lower-right on the lower step, leaning back on his hands, looking up at her. Both are in focus. The porch railing behind, the grey Atlantic beyond, fog on the water. Two ceramic mugs on the step between them, steam rising. The gap between them — six inches — is visible and charged. Late afternoon overcast, amber cloud-break from the left catching both their faces. Shot on full-frame mirrorless, 35mm at f2.8, both faces sharp. Natural overcast light only. Hyperrealistic documentary. 9:16 vertical.

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 5 · LoadImage · image

WhatsApp Image 2026-07-21 at 11.47.35 PM.jpeg

Input media

3

Source images and video this run consumed.

character_ref_00345_.png

node 4 · 1.4 MB

WhatsApp Image 2026-07-21 at 11.47.35 PM.jpeg

node 5 · 99 KB

character_ref_00348_.png

node 6 · 1.4 MB