DaVinci MagiHuman

davinci-magihuman

DaVinci MagiHuman

davinci-magihuman

Expressive image-to-video avatar generation with natural facial performance, realistic body motion, accurate A/V sync, and optional driving audio for lip-sync mode.

Added Apr 3, 2026

Starting Price

From $0.250 per video

Final price depends on the selected settings and is shown before generation.

Model Type

image-to-video

Settings

Generation controls available for this model.

Output Format

up to 1,080p

Default Duration

5

30 duration options

Driving Audio URL

Text

Default

N/A

Optional audio URL for lip-sync mode. If omitted, audio is generated from the prompt.

Duration

Select

Default

5

Options (30)

1 second, 2 seconds, 3 seconds, 4 seconds +26 more

Length of the generated video in seconds.

Guidance Scale

Number

Default

5

Optional classifier-free guidance scale (0-20).

Inference Steps

Number

Default

8

Optional denoising steps (1-50).

Resolution

Select

Default

256p

Options (4)

256p, 540p, 720p, 1080p

Output resolution.

Safety Checker

Toggle

Default

Yes

Run prompt and image safety checks before generation.

Seed

Number

Optional seed for reproducible output.

Benchmarks

No benchmark data is available yet for this model.

Examples

Loading examples…

Compare DaVinci MagiHuman with similar models from the same provider or model family.

MiniMax H3 Max Extend

minimax/h3-max/extend-video

Continue an existing video with a prompt describing what happens next. Add 5–15 seconds of new footage at 480p through 2K, returning the full extended video or just the continuation. Source videos must be MP4 or MOV, 1.625–60 seconds, at most 50 MB, with an aspect ratio between 0.4 and 2.5.

MiniMax H3 Max Lip Sync

minimax/h3-max/lip-sync/image-to-video

Animate a portrait or character image from supplied audio with transcription-guided lip sync. Audio must be at least 5 seconds; longer inputs are clipped to the first 15 seconds. Supports talking and singing clips from 480p through 2K.

Wan 3.0 Prime Video Edit

alibaba/wan-3.0-prime/video-edit

Accelerated Wan 3.0 editing for an existing video with optional image or audio references. Uses the first 15 seconds of the source and supports 2–15 second output at 480p, 720p, or 1080p.

Wan 3.0 Prime Video Extend

alibaba/wan-3.0-prime/video-extend

Accelerated video extension that appends 2–30 seconds with optional target last-frame guidance. Source audio is preserved, and clips longer than 120 seconds use their final 120 seconds as context.

Wan 3.0 Video Edit

alibaba/wan-3.0/video-edit

Edit an existing video with natural-language instructions and optional image or audio references. Uses the first 15 seconds of the source and supports 2–15 second output at 480p, 720p, or 1080p.

Wan 3.0 Video Extend

alibaba/wan-3.0/video-extend

Extend an existing video by 2–30 seconds with optional target last-frame guidance. Source audio is preserved, and clips longer than 120 seconds use their final 120 seconds as context.