That is the whole point, and it is what separates a good result from a generic one. The model carries across hair colour and shape, facial hair, glasses, clothing and expression, then rebuilds the rest in fleece and yarn. Distinctive features translate best — a beard, strong glasses, unusual hair colour — while a plain, evenly lit face gives it the most to work from.

No, and that is deliberate. This turns your own face into a puppet in the general style of felt television puppetry — fleece, yarn, googly eyes. It does not reproduce named characters from a particular series, which are somebody else's copyrighted designs. Your own face in felt is yours to use.

It is rendered to look photographed: fabric fibre visible in the fleece, real studio lighting on the surface, stitching and seams where a puppet would have them. That is why it reads as an object someone could actually hold rather than a flat illustration of one.

A straight-on, evenly lit shot from the chest up, with your face unobstructed. Harsh side shadow, a steep angle, sunglasses, or a busy background all cost the model the detail it needs to make the resemblance land. A plain backdrop and a clear expression convert best.

Yes — describe it in the prompt. Ask for larger or smaller googly eyes, a particular yarn hair colour, a fuzzier or smoother fleece, a full-body puppet with arms rather than head and shoulders, or a specific background. A run you do not like costs nothing to redo.

A single clear subject converts most reliably. Groups can work, but every extra face is another likeness the model has to preserve, so the resemblance gets weaker the more people are in frame. For pets, the pet portrait tool is the better-tuned starting point.

The credit estimate appears before you generate and updates with the format and resolution you choose, so you see the cost first. Failed runs are never charged, and new accounts start with free credits — enough to try the look and judge it before spending anything.