Frequently asked.
Training
How long does training take?
~12 minutes once your turn in the queue arrives. Premium quality is ~25 minutes. Rush ($30) jumps you to the front of the queue.
What if my trained portrait looks bad?
First re-train is free. Better photos in (varied angles, expressions, lighting) gets better portraits out. After the second re-train we offer a partial refund.
How many photos do I need?
Minimum 15. Sweet spot is 25–40. Past 50 the marginal improvement falls off and overfitting risk goes up.
Privacy & safety
Do you share my photos?
No. Photos are used only for your specific training job. They are not used to train any other customer's portrait. Deleted from active systems 90 days after delivery.
Can I train on someone else?
Only with their explicit written permission. Our verification step requires their selfie matching every photo in your upload. If they haven't verified, you can't train on them.
What about minors?
All photos are scanned by a multimodal AI guard model before training. Any photo where the person appears under 18 is automatically rejected. We use this for every upload, no exceptions.
Using your trained portrait
What software do I need?
Nothing — generate photos right here in the workshop anytime. If you'd rather work in your own tools, the trained AI portrait model file is a standard .safetensors compatible with ComfyUI, A1111, Forge, Invoke, and Fooocus.
Billing
What payment methods do you accept?
Coming soon. Payment integration is being wired in now — credit card via our merchant of record, plus crypto (BTC, USDC) for those who prefer it.