TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

2bf0a014-0d18-4b02-b733-90ce7d479e72

Queued
Jul 22, 2026, 04:09 PM
Completed
Jul 22, 2026, 04:10 PM
Execution time
14.6s
Outputs
1 · 1.4 MB
Inputs
3
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00366_.png

node 3 · 1.4 MB

Text prompts

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

[REFS: attach @Elena and @Aidan face refs] Profile two-shot — both faces seen from the side, filling the vertical frame. The woman's profile on the LEFT looking RIGHT. The man's profile on the RIGHT looking LEFT. They have leaned in without realizing it — a gap of about four inches between their faces. The soft grey ocean and sky show through the gap between their profiles through the railing behind. Her profile: the line of her nose, lips slightly parted, eyelashes, the strand of hair across her cheek, her grey-green eye looking at him. His profile: jaw, stubble, the scar through his eyebrow, his mouth set but softening, his brown eye looking at her. The framing is symmetrical — two faces, one gap, the world between them. Shot on full-frame mirrorless, 85mm at f2. Both profiles sharp, the ocean melting soft between them. Natural overcast with amber cloud-break catching the bridge of her nose and his cheekbone from the left. Hyperrealistic — every pore, lash, stubble hair, lip texture visible. 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_00360_.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