My understanding is that the face model limitation may have been deliberate to avoid deepfakes of celebrities, etc. Interestingly, DALL-E can nonetheless at least sometimes do perfectly reasonable faces, either as photographs or in various art styles, if they’re the central element of a scene. (And it keeps giving me photorealistic faces as a component of images where I wasn’t even asking for that, meaning that per the terms and conditions I can’t share those images publicly.)
FWIW, OpenAI just changed the requirements on face samples, loosening it considerably, so now you can post most of your face samples if you want. And people have begun doing so: “And in case you were wondering, #dalle2 is able to create VERY REALISTIC faces.”