61bfa5e1-1e2f-4ad3-a3f6-72411b07d9d0

@Aria, extreme close-up on the eyes and upper face, head slightly lowered, jaw tight, rain streaming down her skin so tears and rainwater are indistinguishable, wet strands of hair plastered across the forehead. Expression: raw fury held in check with grief underneath, eyes fixed hard off-lens left, not blinking. Wardrobe: @Aria/Night-Rain, the collar of a soaked coat just visible at the bottom edge, drenched. Set: on the empty road of @RainStreet/Road at night, only dark wet-street bokeh and a far smear of streetlight behind her, thrown well out of focus. Composition: extreme close-up, eyes on the upper third, tight crop cutting the top of the head and below the nose, slight low angle. Camera: shot on ARRI Alexa 35, Signature Prime 65mm at T2, shallow focus, only the eyes tack-sharp. Lighting: a single motivated cold streetlight edge-keying from camera left, hard 6:1 ratio, deep shadow on the right of the face, cool sodium rim on wet skin, the rest falling to black. Color: ARRI Reveal naturalism, desaturated cool, deep clean blacks. Texture: fully unretouched skin, visible pores, freckles across the nose, real wet sheen, individual raindrops on the lashes and skin, 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.