d91eb737-b719-46b8-b553-d8973c609e63
- Queued
- Jul 22, 2026, 01:48 PM
- Completed
- Jul 22, 2026, 01:49 PM
- Execution time
- 12.4s
- Outputs
- 1 · 1.3 MB
- Inputs
- 2
- Cached nodes
- —
Outputs
1Click an image to view it full size.
Text prompts
3Over-the-shoulder two-shot into the vanity mirror: a man in a black suit standing behind the seated woman in the red velvet gown, bringing a fine chain around her neck, both faces warm in the reflection, heart pendant at her chest. Warm tungsten, real skin both, film grain, vertical 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 6 · LoadImage · image
WhatsApp Image 2026-07-22 at 6.54.07 PM.jpeg
Input media
2Source images and video this run consumed.