61a6ee11-213f-4cbf-9e9e-72fd44c6700a
- Queued
- Jul 23, 2026, 03:49 PM
- Completed
- Jul 23, 2026, 03:49 PM
- Execution time
- 8.0s
- Outputs
- 1 · 1.2 MB
- Inputs
- 1
- Cached nodes
- 1
Outputs
1Click an image to view it full size.
Text prompts
2Photorealistic frame of the same 32 year old woman seated at a desk at two in the morning, chest up, three-quarter angle to camera left, wearing large closed-back black studio headphones with a gaffer tape repair on the left hinge. Her face is lit almost entirely by two computer monitors just out of frame, cold blue-white 6500K light from the front and slightly below, catching the underside of her brow, the tip of her nose and her lower lip, leaving the upper half of her face in falloff. A weak 2400K sodium streetlamp behind her camera right puts a thin amber rim on her right shoulder and the loose hair on that side, and throws soft horizontal venetian blind bars on painted brick in the deep background. Ceiling light off. Room otherwise dark with milky lifted shadows and visible sensor noise in the black areas. Neutral reading expression, eyes tracking slightly left of lens as if reading text, lips closed. Alexa 35, 50mm Zeiss Supreme Prime at T1.8, focus on the near eye, background falling to soft unreadable shapes. Vertical 9:16 composition, her face in the upper two thirds. Kodak 500T character, low saturation, lifted blacks, unretouched 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
1Source images and video this run consumed.