TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

df1383be-5dd5-4d82-96d0-9c8e83648024

Queued
Jul 27, 2026, 06:09 AM
Completed
Jul 27, 2026, 06:09 AM
Execution time
8.2s
Outputs
1 · 1.5 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00477_.png

node 3 · 1.5 MB

Text prompts

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

last train, A massive, vintage steam locomotive, painted in a deep, matte forest green with tarnished brass accents and sooty highlights, resting motionless. Thick, white steam plumes rhythmically from its tall, conical smokestack and lower piston vents, softly billowing across a deserted, dimly lit stone platform., The locomotive features large, dark steel driving wheels with visible linkages, a prominent cast-iron cowcatcher, and a single, flickering amber lantern mounted on its front, casting a weak, localized glow. Its weathered metallic surfaces subtly reflect the sparse ambient light, indicating age and countless journeys. The steam is dense, opaque, and momentarily catches the light as it escapes, creating a spectral, ethereal presence in the cool, silent air of the station platform, which shows signs of minor wear and dampness.

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

0

This run had no input media — it generated from prompts alone.