3de2bf95-abfc-4cd2-b99a-a399c52babec
- Queued
- Jul 22, 2026, 03:13 PM
- Completed
- Jul 22, 2026, 03:13 PM
- Execution time
- 8.9s
- Outputs
- 1 · 1.5 MB
- Inputs
- 2
- Cached nodes
- 2
Outputs
1Click an image to view it full size.
Text prompts
2[REFS: attach @Elena face ref] Close-up of the woman from the man's lower angle — we are looking UP at her from where he sits on the lower step. She is looking out toward the ocean, not at him. The wind has caught her hair and is pulling it across the right side of the frame in a sweep of dark strands, some lit amber at the edges. Her neck is exposed on the left side — the collar of the oatmeal sweater pulled slightly by the wind. Her expression is distant, somewhere else, somewhere old. The grey sky fills the background above her head. This is his view of her. What he sees when she forgets he's watching. Shot on full-frame mirrorless, 50mm at f1.8. Natural overcast with amber cloud-break from the left catching her hair edges. No fill, no artificial light. Hyperrealistic — individual hair strands, neck skin texture, sweater yarn fibers, the fine hairs at her temple. 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
2Source images and video this run consumed.