Comment by dominicfrei

I'm working on https://photoboost.app, a tool that turns a handful of selfies into professional AI-generated headshots. Think studio-quality photos without the studio — powered by LoRA fine-tuning and smart prompting.

The goal: minimal input, fast turnaround, and results good enough to use on LinkedIn or resumes. Currently experimenting with ways to reduce training time and improve accuracy with as little as 5-8 images. Also exploring automatic gender/style detection to optimize prompts while keeping everything privacy-friendly.

Would love feedback — what would you expect from a tool like this? What features or improvements would make it a no-brainer to use?