1d68539f-a75a-4ede-9c97-411e7d7cee95
- Queued
- Jul 27, 2026, 03:03 PM
- Completed
- Jul 27, 2026, 03:03 PM
- Execution time
- 22.1s
- Outputs
- 1 · 5.6 MB
- Inputs
- 2
- Cached nodes
- —
Outputs
1Click an image to view it full size.
Text prompts
2Medium close-up, side profile of @Aria mid-run down the empty road of @RainStreet/Road, caught between strides, torso leaning into the run, wet hair whipping back off her face, mouth parted in a hard gasp, eyes fixed forward off-lens. Rain drives across her face and streams off her jaw. Wardrobe: @Aria/Night-Rain, soaked coat collar, drenched. Set: dark wet street sliding past behind her, streetlights and reflections thrown to soft streaks, out of focus. Composition: profile framing, her face in the right-center, lead room ahead at frame left into the direction of travel, motion-implied. Camera: shot on ARRI Alexa 35, Signature Prime 50mm at T2.5, shallow focus on her face, background melted. Lighting: motivated streetlight raking from the side as a hard cool key, deep shadow on the far cheek, sodium rim on wet skin, 4:1. Color: ARRI Reveal, desaturated cool, deep blacks. Texture: unretouched skin, pores, freckles, real water on the face, wet strands, 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.
Input media
2Source images and video this run consumed.