I gave myself a monster makeover with ChatGPT, here’s how you can do it, too
The best part of Halloween, besides the candy, is the costumes. I’ve enjoyed the few times I’ve been able to create particularly elaborate looks, and I always love seeing how others embrace the spooky season. I was running out of time to do anything on this scale this year, but for fun I decided to see how ChatGPT could digitally transform me for Halloween, perhaps inspiring a look for next year based on the classic monsters of Universal Horror.
ChatGPT’s image tools, when paired with a good selfie, can go surprisingly far in creating visual alter egos. I wouldn’t exactly call the results my undead doppelgangers, but at least in some cases I could believe I had walked away from the D-movie ripoff of a Universal classic. You can see some of the best results and the prompts behind them below.
Vampire Weekend
I started with a vampire, naturally. I wanted to look like a 1930s vampire lord, with sharp cheekbones, a widow’s visor and an elegant black cape. I quickly discovered that there was only so much ChatGPT could do before it stopped looking like me. Still, there are some key phrases that have worked really well for all of my portraits, as I discovered here. This also helped give the image the expression and mood I wanted.
The prompt ended with: “A hyper photorealistic portrait of the man from the reference photo in classic vampire form, retaining his true facial features but with pale skin, red lips and clearly visible fangs bared in a predatory expression. He wears a black cape with a high collar and a formal shirt. The lighting is moody candlelight with a golden glow to one side, evoking the interior of an aristocratic Gothic castle.”
Hair of the dog
The Wolfman was next. Again, it took some experimentation to get a look that wasn’t just me with dog ears and a nose, but also a wolf face without having anything to do with my actual appearance. The result is similar to the character in the movie, although I can’t help but feel upset because my hair is out of control.
The final prompt used is, “A hyper-photorealistic portrait of the man from the reference photo transformed into a wild wolf-man. His face remains clearly recognizable but covered in realistic fur, with sharp teeth, yellow eyes, and a snarling snarl. The background is a moonlit forest interior or old cabin, with atmospheric shadows and cool tones.”
Mom man
I had similar reservations with the mummy costume, just as I love all (but one) of the many films featuring them. I didn’t want this one to be too covered to see that it’s me or lack enough bandages to make it clear that it’s a mummy. After a few tries, referencing how you could almost see my skin made the image very successful.
The prompt is, “A hyper-photorealistic portrait of the man in the photo completely wrapped in aged, cracked bandages, his eyes and mouth just visible beneath. His skin shows slightly beneath the wrappings, preserving the appearance of his face. The setting is an ancient tomb lit by torchlight, with dusty air and cracked stone walls. The tone is eerie and warm sepia.”
I didn’t intend to give myself such sad eyes with Frankenstein’s Monster, but the vagaries of AI image creation meant that if I didn’t mention a serious or dark look, the end result became haywire. Plus, the coloring had to be specific to avoid it looking like a bright cartoon green or just my normal skin tone, an arguably even more unsettling option.
The prompt is, “A hyper photorealistic portrait of the man in the photo transformed into Frankenstein’s monster. His skin is gray-green with realistic texture and metal bolts protruding from his neck. His expression is grim and he wears a dark coat over a sweater. The background is a dark industrial stone wall lit by moody, cinematic lighting reminiscent of a 1930s laboratory.
In reality, the hardest image to make is the top one with all of these elements together. Getting the digital characters together so that they were still me and the monster, in the right place and looking like a portrait, took about 20 attempts, and I still see more flaws in them than in the individual portraits. Still, if you want to have a Monster Mash featuring you, you, and you, try this long and complex prompt built from a mash-up like Frankenstein’s monster himself:
“Create a hyper-photorealistic group portrait featuring four classic movie monsters, each transformed from the face of that man in the attached reference photo through expert prosthetic-style makeup and cinematic lighting. The monsters are a wild wolf-man with sharp teeth and glowing eyes, a vampire in a black cape with pale skin, red lips, and clearly visible fangs; tattered bandages that still reveal parts of the man’s face in below, they are posed together in a well-lit gothic library. The lighting is warm and reminiscent of vintage Hollywood studio portraits. Each monster must remain distinct but visibly share the same face, as if all were played by the same actor.
Follow TechRadar on Google News And add us as your favorite source to get our news, reviews and expert opinions in your feeds. Make sure to click the Follow button!
And of course you can too follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp Also.
The best business laptops for every budget
