TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

560d0265-0ec4-4d49-b20e-78673e71b4e9

Queued
Jul 27, 2026, 03:06 PM
Completed
Jul 27, 2026, 03:07 PM
Execution time
20.4s
Outputs
1 · 6.5 MB
Inputs
2
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00551_.png

node 3 · 6.5 MB

Text prompts

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

Medium-long shot of @Aria caught in a stumble on the wet road of @RainStreet/Road: her leading foot has skidded out on a slick patch of asphalt, her body pitched off-balance, both arms flung wide to catch herself, weight dropping, face flashing with alarm. Wardrobe: @Aria/Night-Rain, soaked coat flaring with the lurch, wet jeans and boots. Set: black reflective asphalt with a bright specular sheen where she slipped, streetlight reflections smeared, the empty street around her. Composition: medium-long, full figure, @Aria off-center and tilted to convey instability, generous space around her, low-ish angle. Camera: shot on ARRI Alexa 35, Signature Prime 32mm at T2.8, deeper focus, honest and slightly wide. Lighting: motivated cold streetlight, hard reflections on the wet ground under her skidding foot. Color: ARRI Reveal, desaturated cool, deep blacks. Texture: real splash and water spray off the slipping boot, rain in the air, wet fabric, no CGI. Photorealistic cinematic still, prestige crime-drama grit, 9:16.

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

2

Source images and video this run consumed.

character_ref_00545_.png

node 4 · 6.2 MB

character_ref_00538_.png

node 5 · 6.6 MB