# daVinci-MagiHuman FAQ

## What is daVinci-MagiHuman?

A 15B-parameter open audio–video model from Sand.ai and GAIR Lab (SJTU) that turns a portrait plus text or audio into a lip-synced talking clip. This site hosts an online generator for it.

## Is daVinci-MagiHuman free?

The open weights and code are released under Apache 2.0 by their authors. This hosted site bills generation in credits.

## What inputs does it need?

A face image plus driving text or audio; exact formats and limits follow the hosted studio flow.

## Can it be used commercially?

The underlying model is Apache 2.0, which permits commercial use subject to its conditions. Generated output also depends on this site's terms — review both before shipping.

## How do credits work on this site?

Each US dollar converts to 100 credits. Per the pricing page, a ~10s 720p clip is about 120 credits and a ~10s 1080p clip about 200 credits; check the studio for live totals.

## How do I get the best portrait results?

Use a clear, front-facing photo with even lighting and avoid heavy occlusion, extreme angles, or very low resolution.

## Do credits or subscriptions expire?

One-time credit purchases never expire. Monthly and yearly subscriptions renew automatically and can be changed from the billing page.

Source: https://davinci-magihuman.com