29153c55-16fd-487c-bea8-5838ea762ac0
- Queued
- Jul 27, 2026, 06:15 AM
- Completed
- Jul 27, 2026, 06:15 AM
- Execution time
- 8.9s
- Outputs
- 1 · 1.8 MB
- Inputs
- 0
- Cached nodes
- —
Outputs
1Click an image to view it full size.
Text prompts
2A wide-angle lens captures a desolate, gritty Riverside Station - Ticket Booth @loc_edc7a000bfc34311a5399668120ea91a, rain drumming heavily on the grimy glass roof above. In the midground, a large, rectangular departures board @prop_ad08e79d186b4f4bbbabb439c195a628 flickers erratically, its amber-lit display starkly showing 'LAST TRAIN' and '00:04'. Low-key, hard light from unseen sources casts deep shadows, emphasizing the station's tense, abandoned atmosphere. Cool, desaturated color palette with strong contrast.
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
0This run had no input media — it generated from prompts alone.