TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

a7bf59d9-618b-4ae7-8535-d369239dee84

Queued
Jul 26, 2026, 12:31 AM
Completed
Jul 26, 2026, 12:31 AM
Execution time
7.1s
Outputs
1 · 1.5 MB
Inputs
0
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00438_.png

node 3 · 1.5 MB

Text prompts

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

South Valley, A vast, verdant valley cradled by gently sloping, tree-covered hills. The valley floor is an expanse of short, lush green grass, traversed by a clear, shallow stream that winds its way towards the distant horizon. Softly rounded peaks, partially veiled by a gentle atmospheric haze, define the valley's perimeter, conveying a sense of tranquil seclusion. The absence of any discernible hazards or human presence reinforces its pristine, secure character., The landscape features a palette of rich greens, muted earth tones for the stream bank and occasional exposed rock, and a clear, pale blue sky. A narrow, winding dirt path, trodden smooth by light use, parallels the stream. Sparse groupings of conifer trees with dark green needles stand tall, breaking the expanse of grass without forming dense forests. The air is visibly clean and still, with sunlight catching on the occasional dewdrop or dust motes near the path.

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.