TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

ea10096a-c467-41b5-99e0-b4c339ade58d

Queued
Jul 27, 2026, 02:44 PM
Completed
Jul 27, 2026, 02:45 PM
Execution time
21.2s
Outputs
1 · 6.3 MB
Inputs
2
Cached nodes
1

Outputs

1

Click an image to view it full size.

character_ref_00547_.png

node 3 · 6.3 MB

Text prompts

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

Low tracking shot of @Aria's lower body mid-sprint down the empty wet road of @RainStreet/Road, one boot slamming into a puddle and throwing a crown of backlit spray, the other leg lifting, coat hem and wet fabric whipping. Set: @RainStreet/Road at night, black reflective asphalt, worn lane markings, streetlights and their long reflections streaking, the green subway lamp glow small ahead, no vehicles. Composition: low angle near ground level, camera at shin height, @Aria's legs filling the right two-thirds mid-frame, the deep wet road and streaking lights receding toward the alley mouth. Wardrobe: @Aria/Night-Rain, soaked coat and dark jeans, wet boots. Camera: shot on ARRI Alexa 35, Signature Prime 27mm at T2.8, wide with slight distortion, deeper focus. Lighting: motivated sodium streetlights raking the wet ground, cold, hard specular reflections in the puddles. Color: ARRI Reveal, desaturated cool, deep blacks. Texture: real water spray, individual droplets, wet leather boots, splashing detail, rain streaks in the air, no CGI water. 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