9a096232-eda8-4012-9d18-4cac8f32ecd2

Medium shot: @Aria has skidded to a halt at the mouth of the alley, weight still settling, chest heaving, one hand near the wet brick corner, her head turning sharply to look left into the dark alley. Expression: breathless, braced, dawning dread. Set: the junction where @RainStreet/Road meets the mouth of @RainStreet/Alley, wet brick corner, the green subway lamp glow to one side, the alley's darkness opening at frame left. Wardrobe: @Aria/Night-Rain, soaked coat, hair plastered. Composition: medium shot, @Aria slightly right of center, the black alley mouth occupying frame left as the negative space she turns toward, low headroom. Camera: shot on ARRI Alexa 35, Signature Prime 40mm at T2.5, honest range, shallow-ish focus on her. Lighting: motivated street key from camera right (streetlight plus green lamp spill), the alley side falling to deep shadow, cool, 4:1. Color: ARRI Reveal, desaturated cool, deep blacks. Texture: real wet skin and hair, water dripping, rain in the air, wet brick grain, no smoothing. Photorealistic cinematic still, prestige crime-drama grit, 9:16.

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.