05aeffed-fd9f-4518-97ea-21276e247434
- Queued
- Jul 23, 2026, 03:44 PM
- Completed
- Jul 23, 2026, 03:44 PM
- Execution time
- 7.1s
- Outputs
- 1 · 1.2 MB
- Inputs
- 1
- Cached nodes
- —
Outputs
1Click an image to view it full size.
Text prompts
2Photorealistic casting portrait of a 32 year old woman, head and shoulders, facing camera directly, neutral expression, eyes to lens. Long oval face, high flat cheekbones, slightly hooded grey-green eyes, thin upper lip, faint natural asymmetry with the left corner of the mouth sitting lower than the right. Fair skin with a cool undertone, visible pores across the nose and cheeks, faint freckling on the nose bridge, no makeup whatsoever, soft permanent shadows under both eyes, slightly dry skin on the lower lip. Ash brown hair, shoulder length, grown out of an amateur home haircut, unwashed for three days with faint oil sheen at the roots, tucked behind the right ear, falling loose on the left. Plain charcoal t-shirt, no jewellery visible. Lit by a single large softbox at 5600K from front and slightly above, plain mid-grey seamless backdrop, shot on Alexa 35 with a 50mm Zeiss Supreme Prime at T4, sharp focus on the eyes. Unretouched documentary casting photograph, natural skin texture, honest and slightly tired, not glamorous, not beautified.
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.