Picture this: a woman in an elaborate black gown, her face painted in delicate skeleton art, orange marigold flowers tucked into her hair. She stands beside an ornate vintage carriage as candlelight flickers around her. The scene looks like it belongs in a dark fairytale — elegant, dreamy, and quietly haunting.
That is the catrina ai trend — a video format blowing up on Instagram this Halloween season. One reel walking through the workflow picked up 4.2K likes in days, and the comments filled with people asking how to make their own version.
Below are three original prompts you can copy and paste — the portrait, the carriage scene, and a slow walk through a marigold archway. Each one comes with a demo video first, so you can see exactly what the prompt produces before you use it.
A quick note so this doesn’t get confused with older posts: my Ghostface post was a photo trend — a horror mask lurking behind you in a still image. This one is different. Here, you become the elegant figure yourself, in a moving video, with marigolds and candlelight instead of a mask. And my Chandramukhi post was a saree horror-heroine transformation. This one has a different aesthetic entirely — skeleton face paint, a black gown, and the warm orange glow of marigolds.
What Is This Look?
The idea behind the catrina ai trend is simple. You start with a clear photo of yourself. From that photo, the AI creates a short cinematic video of you in the Catrina style: elegant skeleton face paint, an elaborate black gown, orange marigolds in your hair, lace gloves, and a veil — set against a dark, dreamy background lit by candles and lanterns.
In the version going viral, creators feed their photo into an AI video tool with a detailed prompt describing the outfit, the face paint, and the setting. The output is a set of photorealistic clips: the same woman in a black gown decorated with marigolds, posed beside an ornate carriage or walking through a candlelit archway, with a soft dark-fairytale filter over everything.
Why is it spreading so fast? Two reasons. First, the look is genuinely beautiful — the contrast of black fabric, white face paint, and bright orange flowers photographs incredibly well. Second, the timing is perfect. With Halloween close, an elegant spooky-season video is exactly the kind of thing people save and send to friends. The prompts below recreate that effect from scratch, in your own words, with your own photo.
A Respectful Note
Before we get to the prompts, one thing matters. Day of the Dead is a real Mexican tradition — a time when families honor and remember loved ones who have passed. The Catrina figure, with her elegant skeleton face and fine clothes, is part of that tradition: a reminder that death comes for everyone, rich or poor, and that remembering the dead can be beautiful rather than frightening.
So treat this look with appreciation, not mockery. The prompts below keep it elegant and respectful — no gore, no jokes about the dead, no turning a meaningful tradition into a cheap scare. Beauty and respect are what make this format work.
How to Make Your Own
Pick a good reference photo. Front-facing, face clearly visible, decent lighting, hair pulled back or down. This photo becomes the character. The cleaner the photo, the more consistent the result.
Open any image-to-video AI tool. Google Flow, Runway, Kling, Luma, Pika, or a similar tool — the prompts below work with all of them. Upload your photo before pasting the prompt, or the face paint will not sit right on your features.
Copy one of the prompts below and paste it in. Each one spells out the face paint, the outfit, the flowers, and the lighting, so the AI does not have to guess anything. If your tool supports a reference image for the outfit, use it — it helps the AI keep the gown consistent across frames.
Generate two or three versions and pick the best. The first try rarely gets the face paint perfect. Once you have a version you like, add a soft, moody background score — gentle strings or piano — since sound makes this format far more cinematic.
Prompt 1: The Catrina Portrait
The classic shot. Elegant skeleton face paint, marigolds in the hair, a black gown, and soft candlelight. This is the version that started the wave, and still the most shareable of the three.
Using AI video generation, create a photorealistic cinematic vertical video (9:16) of an elegant Day of the Dead Catrina portrait, based on the uploaded reference photo. The scene: a young woman with elegant, artistic skeleton face paint — a delicate white base, fine black linework around the eyes, and small floral details on the cheeks — wears an elaborate black gown with orange marigold flowers tucked into her dark hair. She stands in soft candlelight against a dark fairytale background. Keep her face, facial features, and hairstyle exactly as in the reference photo. The movement: she slowly turns toward the camera with a gentle, serene expression. The candle flames flicker softly, warming the edges of the frame. Her gaze stays calm and graceful, like a portrait come to life. Style: photorealistic, warm candlelight against darkness, dreamy dark fairytale atmosphere, smooth slow motion, ultra-detailed. Vertical 9:16. Elegant, beautiful, respectful. No gore, no text overlays, no watermarks.
Worth knowing: the face paint is the heart of this prompt. If the AI gives you a harsh or messy skull, regenerate — the look only works when the paint is delicate and precise, like fine lace on the skin.
Prompt 2: The Carriage Scene
The grand one. A full look beside an ornate vintage carriage — veil, lace gloves, marigolds everywhere, a spooky-but-elegant garden at dusk. This is the version that feels most like a film scene.
Using AI video generation, create a photorealistic cinematic vertical video (9:16) of an elegant Day of the Dead Catrina scene, based on the uploaded reference photo. The scene: a young woman with graceful skeleton face paint wears an elaborate black gown, a sheer veil, and lace gloves. She stands beside an ornate vintage horse-drawn carriage in a spooky-but-elegant garden at dusk. Orange marigold flowers decorate the carriage and her hair. Keep her face, facial features, and hairstyle exactly as in the reference photo. The mood: warm lantern light glows around the carriage. A soft mist drifts through the garden. She rests one gloved hand lightly on the carriage door and looks toward the camera with a calm, regal expression. The scene feels like a dream — mysterious, but never frightening. Style: photorealistic, warm lantern light against dusk-blue shadows, dreamy dark fairytale atmosphere, gentle slow camera drift, ultra-detailed. Vertical 9:16. Grand, elegant, respectful. No gore, no text overlays, no watermarks.
What makes this one work: the carriage gives the AI a reason to build a whole world around you, not just a face. If the carriage looks too plain, ask for more ornament — gold trim, carved details, and marigold garlands are what sell the fairytale feel.
Prompt 3: The Marigold Walk
The cinematic one. A slow-motion walk through a grand archway covered in orange marigolds, candles lining the path, warm golden light against the dark. This is the version people rewatch.
Using AI video generation, create a photorealistic cinematic vertical video (9:16) of an elegant Day of the Dead Catrina walk, based on the uploaded reference photo. The scene: a young woman with artistic skeleton face paint wears a flowing black gown and walks slowly in slow motion through a grand archway covered in orange marigold flowers. Lit candles line the path on both sides, their warm golden light glowing against the darkness. Keep her face, facial features, and hairstyle exactly as in the reference photo. The walk: she moves one step at a time, her gown flowing gently behind her, eyes calm and serene. The candlelight flickers across her gown as she passes. Marigold petals drift softly through the air around her. Style: photorealistic, slow-motion cinematography, warm golden candlelight against darkness, dreamy dark fairytale atmosphere, ultra-detailed. Vertical 9:16. Graceful, cinematic, respectful. No gore, no text overlays, no watermarks.
A small detail that matters: the drifting petals are doing quiet work here. They give the scene gentle motion even when the walk is slow, which is exactly what keeps a slow-motion video from feeling frozen.
3 Mistakes That Ruin the Look
Going gory. Blood, cracked skulls, and horror effects break this format completely. The Catrina look works because it is elegant — delicate paint, fine clothes, warm light. The moment it turns gory, it stops being beautiful and starts looking like a cheap Halloween costume. Keep it graceful.
Skipping the marigolds. The orange flowers are not decoration — they are the signature of the whole look. Without them, the video reads as generic skeleton makeup. The prompts above put marigolds in the hair, on the carriage, and across the archway for a reason. Keep them in.
Using a blurry or side-angle photo. The AI builds the face paint on top of your features. If the photo is blurry, dark, or shot from the side, the paint will sit wrong and the face will drift between frames. A sharp, front-facing, well-lit photo fixes most problems before they start.
A Few Tips That Actually Help
Let the light do the acting. Candlelight, lantern glow, dusk-blue shadows — each prompt uses light to set the mood. If a result feels flat, the lighting is usually the problem, not the face. Regenerate with stronger light direction before you change anything else.
Keep the face paint consistent. In the carriage and walk versions, the same paint design should carry through. If the AI changes the pattern halfway through, the illusion breaks. A clean reference photo and a specific paint description help the AI hold the design steady.
Do not skip the sound. A soft, moody background score — gentle piano, slow strings, distant chimes — turns a good clip into a cinematic one. Without sound, the same video feels unfinished. Search “dark fairytale” or “moody piano” in the Reels audio browser.
Post the three as a series. Portrait, carriage scene, marigold walk — three videos, three days, one series. Series accounts tend to grow faster because people follow to catch the next part. Drop a hint about the next part in each caption.
Learn a little about the tradition. A one-line caption mentioning that Day of the Dead honors loved ones who have passed shows respect — and it makes your post stand out from the ones treating it as just another filter. People notice when a creator actually understands the look they are wearing.
Frequently Asked Questions
What is this format, exactly?
It is an AI video format where your own photo is transformed into a cinematic clip of you in the Catrina style — elegant skeleton face paint, a black gown, orange marigolds, and candlelight. The prompts in this post give you the exact outfit, paint, and lighting instructions.
Which AI tool makes these videos?
Any image-to-video tool works — Google Flow, Runway, Kling, Luma, Pika, and similar tools. The prompts above are tool-agnostic. Start on a free tier, make a test video, and only think about a paid plan if you like the results.
Is this the same as the Ghostface trend?
No. Ghostface is a photo trend — a horror mask lurking behind you in a still image. This is a video transformation where you become the elegant figure yourself. Different format, different result.
Is it okay to use this look if I am not Mexican?
Yes — as long as you treat it with respect. Day of the Dead is a tradition of honoring the dead, and the Catrina figure is widely shared in art and celebration. Keep it elegant, skip the gore and the jokes, and a short respectful note in your caption goes a long way.
Why does my face paint look messy?
Usually the reference photo was blurry, dark, or side-angled. Use a sharp, front-facing, well-lit photo. If the paint still looks off, regenerate — fine linework is one of the hardest things for AI to hold steady, and two or three tries are normal.
Is it okay to use someone else’s photo?
No — always use your own photo. Putting someone else’s face into a transformation video without permission is a deepfake problem, and platforms remove such content. Your face, your fun.
How long does it take to generate one video?
It depends on the tool — usually 2 to 10 minutes. Keep your prompt and photo ready, so apart from generation time your actual work is about five minutes. For the best result, generate two or three versions and post the strongest one.
Final Words
The formula is simple: one photo, one black gown, one crown of marigolds — and suddenly you are the heroine of your own dark fairytale.
So pick a prompt above, upload your photo, and make your video today. And if you like dramatic formats, check out my Ghostface and Chandramukhi posts too — the trending collection gets a new format every week. If you want to read more about AI video tools, this Google Flow guide is useful.
About Pinky Chouhan
Hey, my name is Pinky Chouhan, and I live in India. I am passionate about discovering new AI trends, AI video tools, and social media content ideas. I also have experience in video and photo editing using tools like CapCut, Adobe, InShot, and VN. Over time, I have worked on many editing projects and enjoy experimenting with new creative techniques and AI-powered tools. I regularly share the latest AI trends, video prompts, and creative ideas on The Prompt Master. My goal is to provide simple and practical prompts that anyone can use to create engaging AI videos. Most of the prompts published on this website are designed to be easy to use. You can simply copy a prompt, paste it into Google Flow or a compatible AI video tool, and start creating your video. I will continue sharing new AI trends, useful prompts, editing tips, and creative ideas to help creators make better content and stay updated with the fast-changing world of AI.