745e4f34-2f9e-4ba4-be15-85154fab7862
- Queued
- Jul 10, 2026, 05:31 PM
- Completed
- Jul 10, 2026, 05:32 PM
- Execution time
- 27.5s
- Outputs
- 1 · 17 MB
- Inputs
- 1
- Cached nodes
- 1
Outputs
1Click an image to view it full size.
Text prompts
2Extreme close-up cinematic film still, a 40s woman detective lighting / holding a cigarette between two fingers near her lips, a thin curl of smoke drifting across her face. Cold golden-hour morning light rakes in from screen-left, warm highlights on one cheekbone, deep soft shadow on the other. Face is calm, unreadable, world-weary — eyes looking slightly off-camera, already knowing how the story ends. Faint stray hairs catching the backlight, subtle skin texture, tiny pores, natural realism. Shot on 70mm film, shallow depth of field, creamy out-of-focus background suggesting a blurred suburban crime scene — yellow police tape and pale police-car lights bokeh far behind her. Long detective coat collar just visible at the bottom of frame. Anamorphic lens, subtle lens flare, fine 35/70mm film grain, gentle halation on highlights, muted teal-and-amber color grade, Roger Deakins / David Fincher lighting, prestige-drama cinematography. Photoreal, hyper-detailed, 8k, sharp focus on the eyes, dramatic negative space. No text, no watermark. --ar 21:9
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.