5651cd4f-6e52-4087-a817-7e27857e8387
- Queued
- Jul 22, 2026, 01:25 PM
- Completed
- Jul 22, 2026, 01:26 PM
- Execution time
- 18.8s
- Outputs
- 2 · 2.3 MB
- Inputs
- 1
- Cached nodes
- —
Outputs
2Click an image to view it full size.
Text prompts
3[SHOT 1.02 | REFS: @Wife → 1000050543.png, @MakeupRoom] @Wife seated at the vanity of @MakeupRoom, seen as her reflection in the globe-bulb mirror. She is mid-stillness during final touches, chin slightly up, her eyes lifting to catch someone behind her in the glass — a small private warmth beginning at the corners of her eyes. Wardrobe: @Wife/Gala-Gown, @Pendant already at her collarbone, no fur. Composition: her reflected face in the right-of-centre of the frame, the warm ring of vanity globes framing the mirror as glowing foreground bokeh orbs, the real room soft behind her reflection — layered depth between glass, bulbs and room. Vertical 9:16, correct headroom, her eye line just off-lens. Shot on ARRI Alexa 35, Signature Prime 50mm at T2.0, shallow honest falloff. Motivated light only: the warm tungsten vanity globes as a soft wraparound key, gentle 2:1 ratio, deep amber. Kodak 2383 emulation, warm naturalistic palette. Real unretouched skin with visible freckling and pores under the evening makeup, natural specular only where skin truly shines, fine grain. No beauty filter. 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.
1 other text field— 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
Input media
1Source images and video this run consumed.