f9312989-1d01-4666-99fd-c44272b8341d
- Queued
- Jul 27, 2026, 12:56 PM
- Completed
- Jul 27, 2026, 12:56 PM
- Execution time
- 20.0s
- Outputs
- 1 · 5.2 MB
- Inputs
- 3
- Cached nodes
- 3
Outputs
1Click an image to view it full size.
Text prompts
2Worm's-eye view: camera lying flat directly on the oak dresser surface, lens tilted steeply upward along the wood grain toward @Maya, who stands over the open drawer. The dresser top stretches away in the extreme foreground, sharp wood grain running to a low horizon line at the drawer edge. @Maya is above and slightly behind that line, phone (@Phone) pinned between her ear and raised shoulder, head tilted down toward her hands as she settles folded clothes into the drawer — eyeline down on her task, never toward the camera. A relaxed half-smile, easy, mid-conversation, unaware of the lens. Wardrobe: cream waffle-knit sweater, black trousers, @RingNew on her left hand. Steep low upward angle, foreground wood surface dominant and soft, her face small and higher in frame, white wall and dark curtains behind. 35mm, T2.8. + REALISM + LIGHT + STYLE Negative (this shot): looking at camera, eye contact, direct gaze, high angle, eye-level, phone in hand, both hands to face, shocked expression, ring box in frame, staged posing, daylight, beauty-filter skin
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
3Source images and video this run consumed.