e4972239-823f-4119-a1a0-37bd59ada5d5
- Queued
- Jul 20, 2026, 06:22 PM
- Completed
- Jul 20, 2026, 06:23 PM
- Execution time
- 8.8s
- Outputs
- 1 · 1.3 MB
- Inputs
- 1
- Cached nodes
- 1
Outputs
1Click an image to view it full size.
Text prompts
2A grey sedan seen from behind, small in the upper third of the vertical frame, driving alone on a narrow coastal road that cuts through heavy morning fog. The road is wet, reflecting the white sky. On both sides: dark pines, barely visible through the mist. The car's brake lights are the only colour in the frame — two small red points in a world of silver and grey. The road stretches ahead into fog, disappearing. The lower two-thirds of the frame is wet asphalt and fog, creating massive negative space below the car — loneliness made visual. Vertical depth: road surface fills bottom frame, car small in upper-mid, fog erasing the horizon at top. Shot on full-frame mirrorless, 85mm at f4 — telephoto compression makes the fog look thick and the road feel endless. Natural flat overcast light, no sun visible, no colour grade, no cinematic warmth. Hyperrealistic — water beading on asphalt, mist droplets in the air, the sedan slightly dirty from long driving. The feeling of arriving somewhere after driving for a very long time. 9:16 vertical.
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
1Source images and video this run consumed.