TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

ca756287-cafa-4150-8ac2-c8744b659241

Queued
Jul 27, 2026, 12:54 PM
Completed
Jul 27, 2026, 12:54 PM
Execution time
19.6s
Outputs
1 · 5.7 MB
Inputs
3
Cached nodes
3

Outputs

1

Click an image to view it full size.

character_ref_00532_.png

node 3 · 5.7 MB

Text prompts

2
Promptnode 1 · PrimitiveStringMultiline · valueCharacter Description (your input)

Camera resting low on the oak dresser top, looking up and across at @Maya as she stands at the open drawer. Her phone (@Phone) is pinned between her ear and raised shoulder, head tilted to hold it, both hands still busy settling folded clothes in the drawer below frame. She wears a soft, easy smile, mid-conversation, relaxed and unaware. Wardrobe: cream waffle-knit sweater, black trousers, @RingNew on her left hand. Foreground: soft out-of-focus edge of the dresser top and a corner of the drawer; background: white wall, dark curtains and cool night window softly falling off. Low table-level angle looking slightly up at her face, waist-up, natural headroom. 40mm, T2.8. + REALISM + LIGHT + STYLE Negative (this shot): phone held in hand, both hands up to face, ring box visible in frame, worried or shocked expression, looking down at camera, high angle, daylight, beauty-filter skin

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.

Input media

3

Source images and video this run consumed.

character_ref_00530_.png

node 4 · 6.2 MB

character_ref_00497_.png

node 6 · 5.8 MB

character_ref_00499_.png

node 7 · 5.9 MB