de63e792-a198-4beb-91c6-d7b1d36f99aa
- Queued
- Jul 22, 2026, 01:37 PM
- Completed
- Jul 22, 2026, 01:37 PM
- Execution time
- 16.1s
- Outputs
- 1 · 1.1 MB
- Inputs
- 3
- Cached nodes
- 1
Outputs
1Click an image to view it full size.
Text prompts
4[SHOT 1.03 | REFS: @Wife → 1000050543.png, @Husband → 1000050544.png, @MakeupRoom] Over-shoulder two-shot into the vanity mirror. In sharp foreground, the backs of both their heads — @Wife seated, @Husband standing close behind her; in the mirror reflection beyond, both their faces together. He is lowering @Pendant's chain over her head with both hands, about to bring it to her throat, his head dipped near her ear. Her chin lifts, eyes on his reflected face, a soft held breath of a smile. Wardrobe: @Wife/Gala-Gown with @Pendant, @Husband/Crowd. Composition: the two real heads flank the lower frame as dark out-of-focus masses; the lit reflection sits centre in the top two-thirds — three planes of depth (real backs / mirror glass / reflected room). Vertical 9:16. Shot on ARRI Alexa 35, Signature Prime 40mm at T2.0. Motivated warm tungsten key from the vanity globes camera-right shaping both reflected faces, gentle fill, deep amber falloff to black. Kodak 2383 emulation, warm naturalistic grade. Real skin texture on both, her freckles and his stubble visible, honest soft shadow, fine film grain, faint warm haze in the globe light. Photorealistic cinematic still, prestige production, 9:16.
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.
2 other text fields— sigmas, filenames, and other non-prompt strings the logger swept up
node 4 · LoadImage · image
WhatsApp Image 2026-07-22 at 6.54.06 PM.jpeg
node 6 · LoadImage · image
WhatsApp Image 2026-07-22 at 6.54.07 PM.jpeg
Input media
3Source images and video this run consumed.