TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

4aa0e08a-a7e0-40f6-b3bf-9a0b5249c40b

Queued
Jul 14, 2026, 01:27 PM
Completed
Jul 14, 2026, 01:28 PM
Execution time
10.2s
Outputs
1 · 1.5 MB
Inputs
2
Cached nodes
2

Outputs

1

Click an image to view it full size.

character_ref_00187_.png

node 3 · 1.5 MB

Text prompts

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

Front-on half-body shot, slight low angle, of a young woman in a navy-blue ribbed knit sweater and dark jeans walking toward camera down the corridor, carrying a tall stack of six old hardcover books held up so it completely hides her face — only long auburn-red hair visible above the books and her freckled hands gripping them. Warm backlit sun-shafts behind her, arched windows on one side, deep perspective hallway. shot on Arri Alexa, 35mm anamorphic lens, shallow depth of field, warm golden afternoon sun-shafts, dust motes, polished speckled terrazzo floor, red brick walls, tall arched windows, teal-shadow amber-highlight cinematic grade, fine film grain, photoreal, face visible, warped feet, extra limbs, deformed hands, bent architecture, cartoon, cgi, plastic, blurry, low-res, watermark, text, 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_00177_.png

node 4 · 1.6 MB

character_ref_00126_.png

node 5 · 1.3 MB