a1d73365-5efa-42b1-82e0-d5142152c6bc
- Queued
- Jul 27, 2026, 04:54 PM
- Completed
- Jul 27, 2026, 04:54 PM
- Execution time
- 24.6s
- Outputs
- 1 · 6.2 MB
- Inputs
- 4
- Cached nodes
- 4
Outputs
1Click an image to view it full size.
Text prompts
2Medium two-shot in @RainStreet/Alley: @Aria has grabbed @Dylan's forearm and sleeve with both hands, pulling at him, half-pleading up into his face, drenched and desperate; @Dylan half-turned back toward her, jaw tight with irritation, his weight already shifting to pull away. @Aria soaked, @Dylan dry. Set: the narrow alley, wet brick close on both sides, rain pouring, the caged wall lamp pooling cool light on the pair, warm window spill above. Composition: medium two-shot, @Aria left and lower reaching up, @Dylan right and taller, the grip on his sleeve central in frame, walls compressing. Camera: shot on ARRI Alexa 35, Signature Prime 40mm at T2.5, both readable, shallow-ish focus. Lighting: cool caged-lamp key from the side, deep shadow, 4:1. Color: ARRI Reveal naturalism, desaturated cool, deep clean blacks. Texture: @Aria's wet unretouched skin and dripping hair, real wet fabric bunched in her grip, @Dylan's dry skin, rain, 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
4Source images and video this run consumed.