3b0559d6-08a1-4180-92ea-b67fbc2e796c
- Queued
- Jul 23, 2026, 02:58 PM
- Completed
- Jul 23, 2026, 02:58 PM
- Execution time
- 11.1s
- Outputs
- 1 · 1.3 MB
- Inputs
- 4
- Cached nodes
- 4
Outputs
1Click an image to view it full size.
Text prompts
3[REFS: attach @Aidan face ref] Close-up of the man sitting on the lower porch step, looking slightly UP and to the LEFT. He has just heard something that stopped him. His expression: still processing, the words still landing — mouth slightly open, eyes soft and stunned, the look of a man who just heard someone reveal something enormous and fragile and then walk away before he could respond. His brow is furrowed but not with confusion — with the weight of wanting to say the right thing and having no words. On the LEFT edge of frame, soft and out of focus: the woman's hip and arm passing by him at his eye level — she is standing, walking past him, exiting. Her oatmeal sweater and dark hair are blurred shapes moving through the left side of frame. She is leaving. He is staying. Behind him: the porch railing, the grey Atlantic, overcast sky. The two mugs still on the step — both cold now, untouched. Shot on full-frame mirrorless, 50mm at f1.8. His face sharp on the right, her passing figure soft on the left. Natural overcast light, fading amber. Hyperrealistic — every pore, stubble hair, the moisture in his eyes, the tension in his jaw. 9:16 vertical.
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.
1 other text field— sigmas, filenames, and other non-prompt strings the logger swept up
node 5 · LoadImage · image
WhatsApp Image 2026-07-21 at 11.47.35 PM.jpeg
Input media
4Source images and video this run consumed.