b27669ed-f769-4033-a6c3-90a5527ffaf0
- Queued
- Jul 26, 2026, 12:31 AM
- Completed
- Jul 26, 2026, 12:31 AM
- Execution time
- 6.8s
- Outputs
- 1 · 1.6 MB
- Inputs
- 0
- Cached nodes
- —
Outputs
1Click an image to view it full size.
Text prompts
2Outside The Latchkey Tavern, The weathered, dark stone facade of The Latchkey Tavern stands under a heavy, overcast dawn. A robust, dark oak-paneled doorway with tarnished brass hinges serves as the entrance. The uneven cobblestone street in front is slick and dark with recent rain, reflecting the ambient light in glossy sheens and shallow puddles. A persistent, cool mist hangs in the air, gradually thickening into a dense, swirling fog that begins to obscure the upper reaches of the tavern and the street beyond., Above the main door, a creaking, wrought-iron sign with faded, hand-painted lettering reads 'The Latchkey Tavern.' Two narrow, arched windows with small, grimy panes of leaded glass flank the entrance, emitting a very faint, warm amber glow from deep within. The rough-hewn stones of the facade are a mixture of dark grey and earthy brown, streaked with patches of dark green moss and lichen. The wooden door frame is thick and worn smooth in places. Distant, indistinct shapes of other period buildings occasionally ghost into view through the shifting fog, hinting at a larger, equally ancient urban setting.
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.