e6ca0679-57d2-48f9-b9ab-ee40e06831c5
- Queued
- Jul 13, 2026, 02:57 PM
- Completed
- Jul 13, 2026, 02:57 PM
- Execution time
- 10.5s
- Outputs
- 1 · 1.4 MB
- Inputs
- 1
- Cached nodes
- —
Outputs
1Click an image to view it full size.
Text prompts
2Empty plate, small American college dorm room, single bed against the wall, cluttered desk, string lights, band posters, laptop glow, warm messy lived-in feel, night. 9:16 vertical. NIGHT — warm low practical lamp + string lights, cozy at first; add cold hallway light spill from the doorway for the intrusion beat harder dusk light, dust in the air, tension Look: cinematic still, prestige teen-drama aesthetic, photoreal, shot on Arri Alexa, 35mm anamorphic lens, shallow depth of field, gentle volumetric haze, fine film grain, high dynamic range Aspect: 16:9 Negative: cartoon, anime, illustration, cgi look, video-game render, plastic, over-smooth, blurry, low-res, watermark, text, logo, distorted architecture, warped lines
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.