Question 1

How do I use the trained character in a video?

Accepted Answer

After training completes, use @omni-character: in any Omni Reference video prompt. Replace with the request_id returned by this endpoint. The character will be automatically included as an image reference.

Question 2

What makes a good reference photo?

Accepted Answer

A clear, front-facing portrait with good lighting works best. Avoid group photos, heavy shadows, extreme angles, or images where the face is partially obscured.

Question 3

Can I use the same character in multiple videos?

Accepted Answer

Yes. Once trained, you can reuse the character's request_id in as many Omni Reference prompts as you like — you only pay the $0.50 training cost once.

Question 4

How long does training take?

Accepted Answer

Training typically completes in 20–60 seconds. The request will timeout after 5 minutes if training does not complete.