Back to all posts

Developer Offer

Try ImaginePro API with 50 Free Credits

Build and ship AI-powered visuals with Midjourney, Flux, and more — free credits refresh every month.

Start Free Trial

How I Made Monster Portraits Using ChatGPT AI

2025-11-01Eric Hal Schwartz5 minutes read
AI Art
ChatGPT
Halloween

A Spooky AI Experiment for Halloween

The best part of Halloween, aside from the candy, is the costumes. While I didn't have time for an elaborate physical costume this year, I decided to have some fun by seeing how well ChatGPT could digitally transform me into classic Universal Horror monsters.

With a good selfie and some creative prompting, ChatGPT’s image tools can go surprisingly far in crafting a visual alter ego. The results weren't exactly my undead doppelgangers, but some were close enough to look like they belonged in a B-movie horror classic. Here are the best results and the prompts I used to create them.

ChatGPT Halloween

Crafting a Classic Vampire with AI

Naturally, I started with a vampire. My goal was a 1930s vampire lord with sharp cheekbones, a widow's peak, and an elegant black cloak. I quickly discovered that there's a limit to how much ChatGPT can change before the image stops looking like me. However, I found that certain key phrases in my prompt were very effective for setting the expression and mood.

ChatGPT Halloween

The Prompt: "A hyper photorealistic portrait of the man from the reference photo as a classic Vampire, retaining his real facial features but with pale skin, red lips, and clearly visible fangs bared in a predatory expression. He wears a black cloak with a high collar and formal shirt. The lighting is moody candlelight with a golden glow from one side, evoking an aristocratic gothic castle interior."

Unleashing the Inner Wolfman

The Wolfman was next. This required some experimentation to find a balance. I didn't want just me with dog ears, but I also didn't want a generic wolf head that had no connection to my actual appearance. The final result is reminiscent of the movie character, though my expression looks more like I'm having a bad hair day.

ChatGPT Halloween

The Prompt: "A hyper photorealistic portrait of the man from the reference photo transformed into a feral Wolfman. His face remains clearly recognizable but covered in realistic fur, with sharp teeth, yellow eyes, and a snarl mid-growl. The background is a moonlit forest interior or an old cabin, with atmospheric shadows and cool tones."

Unwrapping the AI-Generated Mummy

I had similar concerns with the mummy costume. I love the mummy movies, but I didn't want my face to be so covered in bandages that it was unrecognizable, nor so uncovered that it didn't look like a mummy. After a couple of tries, I found that referencing how my skin could faintly be seen through the bandages made the image work perfectly.

ChatGPT Halloween

The Prompt: "A hyper photorealistic portrait of the man in the photo wrapped entirely in aged, cracking bandages, his eyes and mouth just visible beneath. His skin shows faintly beneath the wrappings, preserving his facial likeness. The setting is an ancient tomb lit by torchlight, with dusty air and cracked stone walls. The tone is eerie and sepia-warm."

Bringing Frankenstein's Monster to Life

I didn't intend to give my Frankenstein's Monster such sad eyes, but the quirks of AI image generation meant that if I didn't specify a serious or somber look, the results went haywire. The coloring also had to be very specific; otherwise, the skin either turned bright green like a cartoon or remained my normal skin tone, which was arguably even more unsettling.

ChatGPT Halloween

The Prompt: "A hyper photorealistic portrait of the man in the photo transformed into Frankenstein’s monster. His skin is green-gray with realistic texture and metal bolts protruding from his neck. His expression is somber, and he wears a dark coat over a sweater. The background is a dim industrial stone wall lit with moody, cinematic lighting reminiscent of a 1930s laboratory setting."

The Ultimate Monster Mash: A Group Portrait Challenge

Truly, the most difficult image to create was the group portrait at the top of the article. Getting all the digital characters to still look like me, embody their monster personas, and be correctly placed in a single portrait took about 20 attempts. Still, if you want to host your own Monster Mash starring you, you, and you again, try this long and complex prompt.

The Prompt: "Make a hyper photorealistic group portrait featuring four classic movie monsters, each transformed from this man’s face in the attached reference photo through expert prosthetic-style makeup and cinematic lighting. The monsters are a savage Wolfman with sharp teeth, and glowing eyes, a Vampire in a black cloak with pale skin, red lips, and clearly visible fangs bared;, Frankenstein’s Monster with green-gray skin, neck bolts, and detailed facial scars, and a Mummy wrapped in aged, tattered bandages that still reveal parts of the man’s face beneath. They are posed together in a well-lit Gothic library. The lighting is warm and evokes vintage Hollywood studio portraiture. Each monster should remain distinct but visibly share the same face, as though all were played by the same actor."

Read Original Post

Compare Plans & Pricing

Find the plan that matches your workload and unlock full access to ImaginePro.

ImaginePro pricing comparison
PlanPriceHighlights
Standard$8 / month
  • 300 monthly credits included
  • Access to Midjourney, Flux, and SDXL models
  • Commercial usage rights
Premium$20 / month
  • 900 monthly credits for scaling teams
  • Higher concurrency and faster delivery
  • Priority support via Slack or Telegram

Need custom terms? Talk to us to tailor credits, rate limits, or deployment options.

View All Pricing Details
ImaginePro newsletter

Subscribe to our newsletter!

Subscribe to our newsletter to get the latest news and designs.