b49a5f64-912d-438c-a132-edb5e9b9c04c
- Queued
- Jul 27, 2026, 04:24 PM
- Completed
- Jul 27, 2026, 04:24 PM
- Execution time
- 21.7s
- Outputs
- 1 · 6.1 MB
- Inputs
- 3
- Cached nodes
- —
Outputs
1Click an image to view it full size.
Text prompts
2Close-up of @Dylan in @RainStreet/Alley, a faint smug curl at the mouth, already half-turning his face back toward @Claire off-lens, his eyes sliding off @Aria with contempt, only lightly rain-flecked and dry. Wardrobe: @Dylan/Night. Set: the alley, caged-lamp key, wet brick soft behind, warm window spill. Composition: CU, face filling the frame, near eye-level, eyeline sliding off-lens. Camera: shot on ARRI Alexa 35, Signature Prime 65mm at T2, shallow, eyes sharp. Lighting: cool caged-lamp key, warm window rim, 4:1, deep shadow. Color: ARRI Reveal, desaturated cool, deep blacks. Texture: real unretouched skin, faint rain flecks, 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
3Source images and video this run consumed.