0e168a2b-c8c8-45d0-96d7-99f34d76c2aa
- Queued
- Jul 16, 2026, 08:27 AM
- Completed
- Jul 16, 2026, 08:28 AM
- Execution time
- 11.5s
- Outputs
- 1 · 1.3 MB
- Inputs
- 1
- Cached nodes
- —
Outputs
1Click an image to view it full size.
Text prompts
2Angle: low-angle medium close-up, her face lifting into frame. IMG: Low-angle medium close-up in a school corridor. A young woman with long auburn-red hair and light freckles kneels on the floor mid-gathering, one book in her hand, and lifts her head sharply to look directly at someone off-frame with an annoyed, exasperated expression — brow furrowed, eyes cutting, jaw tight. Neutral overhead fluorescent light, plain wall softly behind, documentary realism. shot on Sony FX3 with Zeiss prime lens, natural neutral daylight mixed with cool white overhead fluorescents, balanced exposure, low-contrast realistic color grade, Kodak Vision3 emulation, natural skin tones, fine subtle grain, photoreal documentary look, sharp clean focus, negative: golden hour, warm amber glow, dreamy backlight, sun-shafts, god rays, teal orange grade, cinematic haze, fantasy lighting, painterly, warped face,, deformed hands, fused bodies, cartoon, cgi, plastic skin, blurry, low-res, watermark, text, logo
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.