Your own character in any shot: the same face

Plain generation draws a new person each time, but a series of clips, a brand or a blog needs one and the same hero. The “Characters” section trains a model on 4-30 photos of one face, and then you shoot that person in any scene.

  • No subscription
  • Price shown before you run
  • Refund if a generation fails

Create a character

How it works

  1. Open “Characters” and create a hero.
  2. Upload 4 to 30 photos of one person and choose fast or portrait training.
  3. Wait for the training. The price is shown before you run, usually about $3.
  4. In “Image” choose the character instead of a model and describe the shot.

Good to know

A recognisable face

A trained hero keeps the features across poses, angles and settings, so the frames add up to a coherent series.

In video too

A frame with your hero can be animated or passed to “Avatar” so that the person speaks in a clip.

Only faces you may use

Train on your own photos or on pictures of people who agreed. Other people and public figures must not be used without consent.

Price

Training is about $3. Each frame with the hero is paid separately, and the price is shown before you run.

FAQ

How many photos are needed?

From 4 to 30 pictures of one face. The more varied the angles and light, the better the result.

There are two training modes: what is the difference?

Fast is cheaper, portrait catches facial features more precisely. Both results are used in the same way.

Do I need to add anything to the shot description?

No, the service word is added automatically and is not shown to the user.

Your own character in any shot: the same face

Create a character

See also

Models that do this

All models and prices · Video models · Image models

Home · Ready-made presets