TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

35f6c1da-6547-4451-ae3a-f41074133c38

Queued
Jul 14, 2026, 01:01 PM
Completed
Jul 14, 2026, 01:02 PM
Execution time
10.9s
Outputs
1 · 1.3 MB
Inputs
2
Cached nodes
3

Outputs

1

Click an image to view it full size.

character_ref_00170_.png

node 3 · 1.3 MB

Text prompts

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

Low-angle side-profile shot at waist height. A young Latino man in a charcoal grey hoodie, brown tee, dark jeans and white sneakers rushes in from the right and collides body-to-body with a young woman in a navy ribbed sweater and dark jeans coming from the left, captured at the exact moment of impact — both torsos jolting, a stack of old hardcover books bursting upward out of the top of frame. Polished terrazzo floor, warm corridor light, flying dust, motion energy. Sharp focus on the point of collision between them. shot on Arri Alexa, 35mm anamorphic lens, shallow depth of field, warm golden afternoon light, dust motes, teal-shadow amber-highlight cinematic grade, fine film grain, photoreal, static, flat lighting, warped face, extra fingers, deformed hands, wrong outfit, cartoon, cgi, plastic skin, blurry, low-res, watermark, text overlay, logo

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_00156_.png

node 4 · 1.4 MB

character_ref_00126_.png

node 5 · 1.3 MB