TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

c05be1cd-5563-4a21-80a2-620690fbaff5

Queued
Jul 19, 2026, 12:52 PM
Completed
Jul 19, 2026, 12:52 PM
Execution time
4 ms
Outputs
1 · 1.5 MB
Inputs
1
Cached nodes
4

Outputs

1

Click an image to view it full size.

0e0aa045-e401-4ac9-a7c0-e745739d0844_sc00_sh00_t01_seg0_00001_.png

node 3 · 1.5 MB

Text prompts

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

Arjun stands, back to camera, holding a lantern whose light casts his silhouette against the dark rooftop. Arjun stands, back to camera, holding a lantern whose light casts his silhouette against the dark rooftop.

Systemnode 2 · GeminiImageDirect · system_promptCharacter Image Generator (Nano Banana)

Output ONE photoreal cinematic frame. No collage, no text, no watermark, no border, no split panels. The reference images define identity and setting: reproduce the face, hair, wardrobe and location EXACTLY as given. Identity is not open to interpretation - treat any drift from the references as a failure. Frame it as a still from a film: motivated directional lighting, natural skin texture, shallow depth of field, subtle grain. This is the OPENING frame of the shot. It establishes the identity and the look that every later frame must match, so favour a clear, well-lit, unobstructed view of the character over a dramatic one. Nothing precedes it - the references are your only source of truth.

Input media

1

Source images and video this run consumed.

f57f4670f18ed28dd5d18146b90f5ebd.png

node 4 · 784 KB