RIFT
Get Rift

What photo to use for an AI video of yourself

Updated · Reviewed by The Rift team

Short answer

Use a recent photo, face to camera, in soft daylight, with nothing covering your face: no sunglasses, hands or heavy filters. For dances and outfits, add a full-body photo too. In Rift, save yourself as a character from two or three photos, so Spark, Rift's video agent, keeps your look in every video. The same rules hold for pets and products.

A recent photo, face to camera, in soft daylight gives the closest AI video of you. Here is what to pick and what to avoid.

The face photo

The full-body photo

Use one when the video shows your whole body: dances, outfits, sports.

Pets

Products and cars

Save yourself as a character

In Rift, add two or three of these photos once and save them as a character. Then say “me” in any line to Spark and it uses the same face each time, so a series looks like one person.

Quick check before you Make

Ask: could a friend recognise me from this photo at a glance? If yes, it’s a good start.

Questions people ask

Can I use a selfie?

Yes. Hold the phone at eye level, not from below, and turn off beauty filters.

How many photos should I use?

One works. Two or three, saved as a character, keep your look steadier across videos.

Does it matter what I'm wearing?

Only if the video shows it. If you want a specific outfit kept, use a full-body photo in it.

Should I smile?

A relaxed, neutral face gives the most room. The video adds the expression.

Also in: Deutsch · Français · 한국어 · Bahasa Melayu · Nederlands