Video models

Veo 3.1 or Kling 2.6?

Do you want the sound in the take, or the best physical motion from a picture you already have?

The short answer

Google

Veo 3.1

Veo 3.1 brings voices, room tone and effects back in sync with the picture, so a dialogue shot is one generation instead of a render plus a session with a voice engine.

Sound in the same take
Voices, room tone and effects come back with the picture, in sync.
Camera that means it
Dollies, cranes and slow push-ins that read like a real operator.
Faces that hold
Close-ups that keep skin, eyes and expression steady through the move.

The tailor's verdict

Prompt to tryAn old tailor pins a navy jacket on a young man, steps back and says 'now you look like yourself'

Kuaishou

Kling 2.6

Kling 2.6 starts from a still you already like and keeps it recognisably yours, and it is the one to reach for when bodies, fabric or water have to move like the real thing.

Bodies in motion
Fast choreography and sport without limbs melting into each other.
Your photo, moving
Start from a still you already love and keep it recognisably yours.
Fabric and water
Silk, hair, splashes and smoke that follow real physics.

Track at dawn

Prompt to tryA sprinter explodes out of the blocks, then walks back breathing hard, sweat catching the low sun

The next question

Either way the price is quoted before the render runs, and a render that fails is never charged for. If you would rather not choose, the studio picks for you on every ordinary render — this page is for when you would.