AI Hanfu Men Generator — Free Preview First, Your Own Model
See Your Free Preview in Seconds, Before You Pay
Train Your Model Once, Then Nine Hanfu Men Portraits
Studio-Quality Results Without a Studio Visit
Narcis generates a free preview of your hanfu men from one uploaded photo — in seconds, a quick sketch, close but not you yet. To unlock the full pack, you train your model: 12–20 photos, about and we email you when your model is ready. From then on, every hanfu men portrait — this pack, every other pack, the portrait studio — renders from your model in about ten seconds.
The pack is nine professional hanfu men rendered in portrait aspect ratio (2:3) — the shape LinkedIn banners, CVs, and print profiles actually use. Each image shows varied crops, expressions, and light angles so you have real choices, not nine identical files.
Your preview photo is processed on European servers; training photos train your model and nothing else. We do not share your photos with third parties.
/hanfu-men · photo · 3 scenes
Men's Hanfu Portraits

no account · ~15s · the first shot is free
More like this
one model wears them all →all 9 looks — from one photo ↓









How it works
Three steps. Upload, preview, deliver.
1
Drop a selfie
Your free preview streams in seconds — a quick sketch: close, not you yet.
2
Train your model
Add 12–20 photos of yourself. Your model trains in the background — safe to leave, we email you when your model is ready.
3
Nine Hanfu Men portraits, truly you
Every shot renders from your model in about ten seconds — this pack, every other pack, and the Studio.
The men's hanfu register
Hanfu is Han Chinese dress before the Qing — the scholar's robe, the official's round collar, the literatus by his lattice screen. This pack moves through three dynasties. Three looks carry the range: a Tang round-collar robe, the yuanlingpao in deep crimson silk with a soft black futou cap, in a wooden garden pavilion; a Ming scholar's cross-collar daopao in slate-blue or pine-green with a square fangjin cap, in a quiet study; and a Song crossed-collar robe in white or celadon with a pale jade belt, beside a carved wooden lattice. The grammar stays Han-correct throughout — cross and round collars, woven sashes, the futou and fangjin caps, the jade belt — and leaves out the dragon-robe motifs hanfu is so often confused with. Each look is shot from three angles, so the nine portraits read like a real sitting rather than the same photo nine times.
These are photographs, not paintings. The output is photoreal: your face and your features, dressed and lit like a portrait a studio would take — soft daylight through a paper screen, the silk's quiet sheen, the collar's clean seam, the cap matte and distinct. It borrows the cut of the garment and the grammar of the light; it does not turn you into a drama still, an ink painting, or a costume. The closer your upload sits to a clear, front-on photo, the sharper the likeness comes back.
How to photograph yourself for hanfu portraits
Good input, sharp result. The pack forgives an imperfect photo — the free preview shows you the result in seconds — but four small things help.
- Soft, even lightFace a window with indirect daylight on you. Skip the overhead bulb and the hard noon sun — both flatten the face and kill the modeling the pack is built around.
- Front or three-quarter, at eye levelHold the camera level with your eyes. No selfie up-angle, no looking down — the scholarly portrait register wants you square to the lens.
- Plain wall behind youLet the pack build the garden pavilion and the paper-screened study. A clean backdrop means the whole likeness budget goes to your face.
- Come as you areThe futou cap and the hair-wrap sit high at the crown, nothing crossing the face — the pack keeps your facial hair and hairline, so upload the version of you that you want to see standing there.
Frequently asked questions
- What's the difference between the free preview and the paid pack?
- The preview is one hanfu portrait built from your photo, shown in seconds — a quick sketch, close but not you yet. To unlock the full pack you train your model: 12–20 photos, and we email you when your model is ready. From then on, every portrait — three looks (a Tang round-collar robe, a Ming scholar's robe, a Song crossed-collar robe), three angles each — renders from your model in about ten seconds.
- Will it actually look like me?
- That's the whole job. Upload one clear, front-facing photo and the pack keeps your face, your features, your skin and hair — then dresses them in the hanfu. The free preview shows you exactly how close the likeness is before you spend a cent.
- Is this real hanfu or a costume filter?
- It's built to read as real Han Chinese dress, not a party costume — the round and cross collars, the woven sash, the futou and fangjin caps, the jade belt, daylight on silk. It borrows the register of a studio portrait; it doesn't claim to reproduce one specific maker's piece. What you get looks like a photo a studio would take, not a sticker pasted over your selfie.
- Is this hanfu or a Qing dragon robe?
- Hanfu — Han Chinese dress from the Tang, Song, and Ming eras, which is a different tradition from the Qing court robe people often picture. The pack holds the cross and round collars, the sashes, and the jade belt, and deliberately leaves out the Qing dragon-robe motifs, horseshoe cuffs, and rank badges. If you want the scholar's robe rather than the emperor's, this is it.
- How is this different from Midjourney or a free AI photo app?
- Midjourney will paint you a handsome man in a robe — just not you; it invents a face, and usually a muddle of Qing and Tang at that. The free face-swap apps keep your face but render it plastic, the silk smeared and the collar melting. This pack does one narrow job well: your real likeness, in a real men's hanfu, photoreal, nine ways.
- Do I need several photos, or is one enough?
- One clear, front-facing photo is enough for your free preview — a couple of extra angles nudge that likeness a little closer too. To unlock the full pack, you train your model on 12–20 photos; that's what every portrait afterward renders from.
- What if I only have a casual phone selfie?
- Start with the free preview — it tells you in seconds whether the likeness lands. If it doesn't, the prep tips above are the quick fix, and it's almost always the lighting. One good photo beats five poor ones.
- What happens to the photo I upload?
- Your preview photo is processed on European servers. If you train a model, those 12–20 photos are used to train your model and nothing else — delete your model and they go with it. Never sold, never shared with third parties.
- Do I have to be Chinese to wear hanfu?
- No. Hanfu is worn with pride by people of Chinese heritage and embraced by a whole movement that welcomes the curious and the respectful alike. The pack is built to honour the garment — and to keep it Han-correct — not to mock it. Wear it with respect and it's yours to enjoy.
When the hanfu pack fits
- A hanfu portrait for the enthusiast who lives in the movement and wants the three dynasties in one sitting.
- Cosplay or convention dress — the Tang, Ming, and Song registers without renting the robe.
- Diaspora sons picturing themselves in the dress their ancestors actually wore, far from home.
- Fans of historical Chinese drama who want the scholar's register on their own face.
- A profile picture with real character — the stillness of a literatus rather than another snapshot.
- A gift for the hanfu-curious friend who would never book the studio himself.
About narcis
Most AI portrait tools ship every pose, profession, era, and aesthetic in one giant catalog. The output looks like every other AI photo on the internet — a glaze over a stock face. Narcis goes the other way. One tool, one job: turn photos of you into portraits worth keeping. Drop a selfie and your free preview streams in seconds — a quick sketch: close, not you yet. For portraits that are truly you, train your own model on 12 to 20 photos; it trains in the background, and we email you when it is ready. Train once, render everywhere — this pack, every other pack, and the Studio all come out of that one model, about ten seconds a portrait, and it stays yours to retrain or delete. Each pack is hand-curated against actual references — paintings, photographers, registers — and tested on real faces before it ships. See a free preview before you pay, not after. Packs are one-time — no subscription to buy one; Studio, the unlimited composer, is optional at €12/month and every pack includes 30 days of it. No template generator. Built and run by one team, on our own infrastructure.
All images are AI-generated. By using this service, you confirm you are 18+, that any face photo you upload is your own or used with explicit consent. Full Terms



