d5f62ff9-f72c-4ca2-a977-1f798a3278e7
- Queued
- Jul 27, 2026, 03:23 PM
- Completed
- Jul 27, 2026, 03:24 PM
- Execution time
- 20.2s
- Outputs
- 1 · 5.9 MB
- Inputs
- 2
- Cached nodes
- —
Outputs
1Click an image to view it full size.
Text prompts
2Medium shot from directly behind @Aria's shoulders and the back of her head as she runs toward the mouth of the alley, her soaked coat and wet hair filling the lower-center frame, the dark alley mouth and the green subway lamp glow ahead of her growing closer. Set: the end of @RainStreet/Road meeting the mouth of @RainStreet/Alley, wet brick, the alley's darkness opening ahead. Composition: over-the-shoulder-from-behind, her back occupying the near frame, the destination (alley mouth) as the focal point deep ahead with lead room. Camera: shot on ARRI Alexa 35, Signature Prime 40mm at T2.5, focus split between her shoulders and the alley mouth ahead. Lighting: motivated streetlights behind, the green subway lamp glow pulling her forward, cool, the alley ahead falling to deep shadow. Color: ARRI Reveal, desaturated cool, deep blacks. Texture: wet coat fabric, dripping hair, rain in the air, wet brick, 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.