86939cba-c522-4111-bc8f-dd67065091ae

Medium shot framed to the chest of @Aria running down the empty road of @RainStreet/Road in a heavy downpour, her hand raised to swipe the back of her wrist across her cheek and eyes, wiping away tears that are already indistinguishable from the rain streaming down her face. Expression: grief cracking through fury, brow drawn together, mouth trembling, eyes glassy and red-rimmed, utterly drenched. Wardrobe: @Aria/Night-Rain, soaked coat, hair plastered flat and dripping. Set: the dark wet street behind her thrown to soft streaked bokeh, streetlights smearing. Composition: medium shot to chest level, @Aria at a slight three-quarter angle to camera so the face and the wiping hand both read clearly, lead room ahead in her running direction. Camera: shot on ARRI Alexa 35, Signature Prime 40mm at T2.2, shallow focus isolating her, background dissolved. Lighting: motivated cold streetlight keying the face from the camera side, sodium rim on wet skin, deep shadow, soft 3:1. Color: ARRI Reveal naturalism, desaturated cool, deep clean blacks. Texture: unretouched skin, visible pores, freckles, real tears and rainwater sheeting together down the face, wet dripping hair, no smoothing, no glamour. 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.