Case study · TEDxKMCT 2026

Every future named, made into a portrait.

On 31 October 2026 XSEDES ran the X-CAPTURE AI Portrait Booth at TEDxKMCT 2026 on the KMCT campus in Calicut. Guests typed the future they wanted and the booth handed back a portrait of them in it, in about fifteen seconds. It was the first deployment of X-CAPTURE.

Delivered · 31 October 2026 · X-CAPTURE AI Portrait Booth, beta

The day in four numbers

  • Futures imagined 559 booth sessions, three stations
  • AI portraits 520 in the TEDX poster style
  • Generation success 97 % 16 of 536 attempts failed
  • Camera to portrait 15.1 s average, finished and on screen
The brief

A theme about the future. A booth that let guests step into it.

TEDxKMCT 2026, the second season of the TEDx event on the KMCT campus, took "Beyond the Blueprint" as its theme. XSEDES joined as the AI photo booth partner.

The booth had to carry the theme, run through the whole programme from 9:00 am to 5:00 pm and give every guest something to keep. Delivery was to the phone: printing was not part of the service at this edition.

What we built

One booth, two tablets, one style for the day.

The AI Portrait Booth is part of X-CAPTURE, the XSEDES product family for photo and video booths, built by the X-LAB division. The XSEDES team rebuilt and integrated it in September and October 2026.

  1. 01

    One main booth, two tablet stations

    A floor-standing main booth and two tablet stations that joined from mid-morning. The tablets produced 42 % of all portraits, so the load never sat on one machine.

  2. 02

    One style made for the event

    The TEDX style set every portrait as a poster in the event's own visual language, in four layouts, carrying the guest's name, the future they typed in and a line to go with it.

  3. 03

    Delivery to the phone

    Each portrait went home through a QR code on the final screen, using X-CAPTURE Automated Content Delivery. Printing was not offered at this edition.

  4. 04

    Staffed throughout

    The XSEDES team set up, commissioned and ran all three stations for the full day, and wrote the report from the station exports.

On the day

Scan, step in, pose. The booth does the rest.

Guests at the main booth on 31 October 2026: scan the code, tap, step in, pose, and the AI gets to work. Cut for the web: the finished portraits and guest close-ups are left out, and one face near the camera is blurred.

How the day ran

Set up before the programme. Still running after it.

The programme ran from 9:00 am to 5:00 pm. The booth was active from 08:13 to 18:31, 10 h 18 min, covering set-up, testing and use after the programme. Station 2's first entry, at 07:21, was a set-up check.

Activity rose through the morning and peaked in the hour from 15:00. The station figures were added together without adjustment:

StationSessionsPortraitsAvg time
Main booth · floor-standing booth32530415.2 s
Station 2 · tablet station12211314.9 s
Station 3 · tablet station11210314.8 s
All stations55952015.1 s

The engagement report has the hourly chart, the station table and how each figure was counted.

What we learned

A first deployment is a test. Here is what it showed.

X-CAPTURE is in beta. TEDxKMCT 2026 was its first live deployment, so we read the station exports for what to change, not only for what went well.

  1. 01

    Choice keeps people at the booth

    252 retakes were recorded, about one for every two finished portraits. Guests stayed for a better result. More than one style would turn those retakes into second sessions.

  2. 02

    The breaks set the queue

    The busiest hour began at 15:00, with 139 pictures and 86 portraits. Peaks follow the programme breaks, so capacity should be planned for them, not for the daily average.

  3. 03

    A failure needs a next step

    16 of 536 generation attempts failed. Each one could be retried on the spot, so a failure cost a guest seconds, not their portrait.

  4. 04

    Count what happens after the booth

    425 QR codes were shown, 82 % of portraits. The system counts codes shown, not downloads or shares. Measuring the download is the next change to make.

After the event

The portraits, made into one artwork.

As a thank-you to the organising team, XSEDES built all 520 portraits into a photographic mosaic that spells the season's theme, Beyond the Blueprint, in a vertical and a landscape version, with print masters for the campus walls.

Shown here at web size, each portrait is one small tile in the crowd. The full-resolution artwork and the print masters stay with the organisers.

The words Beyond the Blueprint, built from all 520 AI portraits made at TEDxKMCT 2026, each one a small tile.
Beyond the Blueprint, the TEDxKMCT 2026 portrait mosaic: landscape version on wider screens, vertical below.

All 520 portraits come together as the season’s theme. Web cut: the portraits stay soft until they are small tiles in the artwork, so no guest’s face or name can be read.

Partner with us

Bring this to your event.

An AI Portrait Booth designed for your programme, staffed on the day and reported like this afterwards.

Start a conversation