It all begins with your prompt. You need a good solid prompt that clearly states what you want. The Prompt is how you direct the AI, so if your text isn't clear neither will be your output image.
Getting Started
Anyone who’s attempted to generate concept or fan art of their favorite celebrities in scenes from popular series, or has attempted to generate crossover images, will have noticed certain AI models have these actors seemingly locked into a certain age and look. For instance prompting for actors of yesteryear like Ricardo Montalban or Lucille Ball tend to generate images of a distinguished gentleman and matronly redhead. (No need to specify hair color with Lucy.) While the opposite holds true for more recent popular actors like Jenna Ortega or Maisie Williams.
If you’ve read my previous article discussing age prompts and attempted to apply that advice in reverse, sadly, it seldom works. And if it does the results may be even more inconsistent than attempting to write a prompt to generate a consistent age regression for an popular elder statesman actor. But it's not impossible, though you may need to have patience and burn through a few generations.
Begin with a clear character description. What you’ll want, to begin, is to describe the target age with as few descriptors as possible. That seems to work best. Usually. Also, and this one is important, pay attention to your CFG setting.
Some descriptors to try may include: older, old, grownup, aged, age [input your desired age], middle age, matronly, elderly, wizened, mature.
Do they work?
On occasion and depending on your chosen model.
Remember: Write the prompt so it is telling the AI that your chosen actor or other personage is being depicted in a older role. For instance: “Jenna Ortega as the matronly Countess Bathory.” That might work. Results will vary depending on your chosen model. So experiment until you find the model that works for you.
Sticking to a Favorite Model
What to do if you really have a great idea but can’t get the age quite right in the model you absolutely have to use?
Option 1. Create the image you want without the actor’s name in the prompt. Then do a face swap/overlay.
Don’t have access to that sort of tool?
Option 2: Use complete sentences, no syntax shortcuts, with strong descriptors to spell out what you want the character in your image to look like. You can’t force a model to generate a style of image that doesn’t fit its aesthetic framework, but you can sometimes get it to come close.
Examples:
A) This seems to work 50/50: “Jenna Ortega aged 50 years as a matronly Countess Bathory.”
B) This seemed to work better: “Jenna Ortega aged 50 years as a matronly Countess Bathory, wrinkly skin, old woman's face, haggard, tired face and eyes.”
See the difference? Prompt A left quite a bit of room for interpretation whereas Prompt B narrowly defined the desired output. There are pros and cons for both prompts. For instance Prompt A, because it’s not as constricted, may generate a more authentic face whereas Prompt B may output a character barely recognizable to you.
That’s it.
While there are plenty of tools out there these are the basics, at least that I have observed to work within your prompt. No external image processing required.
I hope this was helpful.
Addendum: I very nearly forgot, and this is VERY important. Pay attention to your negative prompt, if you use one. The negative prompt also guides your image output. Check out my gallery. Look for the Countess Bathory images. The one with the younger looking Countess has my stock negative prompt. It's bloated and overwritten. A problem for another article.
Edited for clarity.
