b6c61b78-e8bd-45ff-a5ec-aa348ec2e205
- Queued
- Jul 27, 2026, 02:21 PM
- Completed
- Jul 27, 2026, 02:22 PM
- Execution time
- 13.1s
- Outputs
- 1 · 6.4 MB
- Inputs
- 1
- Cached nodes
- 1
Outputs
1Click an image to view it full size.
Text prompts
2Casting reference portrait of a 43-year-old man, hard neutral expression, professional casting studio. Face: brutal and weathered, heavy thick features, a broken nose healed crooked with a flattened bridge, deep lines, an old scar through one brow, small cold eyes under a heavy brow, several days of grey-flecked stubble. Skin: ruddy and weather-beaten, coarse open pores, broken capillaries across the nose and cheeks, real and unretouched. Hair: shaved close, a grey-flecked buzz, receding at the temples. Build: big and heavy, thick neck, broad and powerful, a bruiser gone slightly to fat, an enforcer. Casting energy: an impatient, dangerous street enforcer, brutal and used to being obeyed, but not the top of the food chain, a hard man who would still flinch at someone worse than him. Capture: neutral mid-grey seamless background, soft even key, medium close-up, 50mm-equivalent at T4, eyes tack-sharp, direct to camera. Photorealistic, coarse skin texture, natural asymmetry, documentary-real, no stylization. Portrait framing. Negative: young, handsome, clean-cut, slim, model, heroic, glamour, plastic skin, airbrushed, symmetrical face, oversaturated, HDR, CGI, cartoon, oversharpened, deformed hands, watermark, text
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
1Source images and video this run consumed.