TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

315dce72-d757-4ade-b2a8-c0b16db34896

Queued
Jul 22, 2026, 04:03 PM
Completed
Jul 22, 2026, 04:03 PM
Execution time
13.9s
Outputs
1 · 1.3 MB
Inputs
3
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00365_.png

node 3 · 1.3 MB

Text prompts

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

[REFS: attach @Aidan and @Elena face refs] Low angle shot from below the porch steps looking UP at both people. Camera is at ground level near the bottom step. The man in the navy henley is on the RIGHT of frame, his face seen from below — jawline, stubble, the underside of his brow — looking across at the woman. The woman in the oatmeal sweater is on the LEFT, also from below, looking down at her own hands around her knees, not at him. The grey overcast sky fills the space between and above their heads through the railing. The two cold mugs are large and soft in the extreme foreground. His expression from below: absorbing what she just said, processing it, choosing his next words carefully. Her expression from below: exposed, regretting saying too much, retreating into herself. Shot on full-frame mirrorless, 28mm at f2.8 from ground level. Both faces readable, slight wide-angle distortion from below giving the shot an intimate unease. Natural overcast light falling from the sky above onto their upturned faces. Hyperrealistic. 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