AI Odissi Generator — Nine Photos From Your Own Model
See Your Free Preview in Seconds, Before You Pay
Nine Odissi from Your Trained Model
Studio-Quality Results Without a Studio Visit
Narcis generates a free preview of your odissi from one uploaded photo. The preview streams in seconds — a quick sketch, close but not you yet. If you like it, you train your model on 12–20 photos of yourself; training runs in the background, and we email you when it is ready. From then on, the full pack of nine — €4,99 — and every other pack and the portrait studio all render from that one model.
The pack is nine professional odissi 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.
Preview photos are processed on European servers. Training photos train only your model — delete your model and they go with it. We do not share your photos with third parties.
/odissi · photo · 3 scenes
Odissi 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 it's ready.
3
Nine portraits, truly you
Every shot renders from your model in about ten seconds — this pack, every other pack, and the Studio. €4,99 one-time.
The Odissi register
Odissi is Odisha's temple dance, and its signature is the one thing every other classical form does differently: silver, not gold. This pack builds three looks around that register. The first is a full temple editorial costume in Odisha ikat silk with a stitched front pleat, the tahiya — a silver filigree headpiece shaped like a temple spire — set above a low bun, a silver hair-parting ornament, jhumka earrings and a silver waist belt, held in the tribhangi stance, the body's three-part curve, with a mudra raised clear of the face. The second is a stage register under raked footlights, the silver catching the light against carved stone-temple architecture. The third is a jewellery-forward close: the tahiya, the silver jhumka, the parting ornament, jasmine in the hair, shot tight enough that the silver reads clean against the ikat silk. Three takes each — colourway, mudra, framing — so the nine portraits read like a real Odissi recital gallery, not the same photo nine times.
These are photographs, not paintings. The output is photoreal: your face and your features, dressed and lit in the register of the form — the ikat silk's texture, the silver catching a clean cool specular against warm skin, the temple stone or scrim soft behind you. It honours the costume, the jewellery and the curved tribhangi line of Odissi; it does not turn you into a cartoon, a painting, or a costume-shop cutout. The closer your upload sits to a clear, front-on photo, the sharper the likeness comes back.
How to photograph yourself for Odissi portraits
Good input, good portrait. The pack forgives an imperfect photo — the free preview shows you the result in seconds — but four small things sharpen it.
- 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 modelling 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 classical register wants you square to the lens.
- Hair back from your faceThe pack sets the tahiya and the parting ornament at your hairline. Hair pulled back into a low bun lets the pack place them cleanly.
- Plain wall, everyday faceLet the pack build the temple architecture and the costume styling. A clean backdrop and a natural face mean the whole likeness budget goes to you.
Frequently asked questions
- What's the difference between the free preview and the paid pack?
- The preview is one Odissi portrait built from your photo, shown live in seconds — you judge the likeness before you commit to anything. The paid pack is nine portraits: three looks (temple editorial, stage register, jewellery-forward close), three takes each, once your model is trained — 12–20 photos, and we email you when your model is ready. €4,99, about ten seconds a portrait.
- 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 costume and the silver temple jewellery. The free preview shows you exactly how close the likeness is before you spend a cent.
- Is this a genuine Odissi look or a costume filter?
- It's built to read as a recital editorial, not a fancy-dress photo — a real ikat-silk costume, the silver tahiya headpiece, the tribhangi stance the form is known for. It treats the form with care; it doesn't claim to copy one specific guru's costume or to stand in for the years of training the dance asks. What you get looks like a portrait a recital photographer would take, not a sticker pasted over your selfie.
- How is this different from Midjourney or a free AI photo app?
- Midjourney will paint you a beautiful dancer — just not you; it invents a face. The free face-swap apps keep your face but render it plastic, with the silver filigree smeared and the ikat pattern melting. This pack does one narrow job well: your real likeness, in a real Odissi costume, photoreal, nine ways.
- Do I need to be a trained dancer to use this?
- No. The pack renders the costume, the jewellery and the stance as a portrait — it's as fitting for a student before a debut recital as for anyone who loves the form and wants the look honoured. It's a celebration of the register, not a claim about your training.
- Can I use these for a debut recital programme, invitation, or profile?
- Yes. The portraits are yours to post, print, and send — a recital programme, an invitation, a school bio, a profile picture, or a framed keepsake.
- Do I need several photos, or is one enough?
- One clear, front-facing photo is enough for the free preview. A couple of extra angles nudge the preview likeness a little closer; training your model takes 12–20 photos and sharpens the result further.
- What happens to the photo I upload?
- Your preview photo is processed on European servers. If you train a model, those photos train only your model — delete your model and they go with it. We do not sell or share your photos with third parties.
- My only good photo is a casual selfie. Will that work?
- The free preview tells you in seconds whether the likeness lands. If it doesn't, the prep tips above are the fastest fix — usually it's lighting. One clear photo beats five blurry ones.
When the Odissi pack fits
- A debut recital keepsake — the costume portrait before the big day arrives.
- A dancer's profile picture or bio photo for a school, a festival listing, or a performance page.
- A recital memento for the student who finished a season of training and wants the silver-and-ikat look captured once.
- Diaspora students of the form picturing the Odisha register from a flat in Singapore, Bhubaneswar, or Berlin.
- A gift for a dancer — the daughter, the teacher, the friend — who lives the art but rarely sits for a portrait.
- Trying the tahiya and the silver jewellery set before you commit to the full costume rental for a real shoot.
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



