Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksEarn crypto
  1. Models
  2. Video

DaVinci MagiHuman

Try Model

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

Details

Starting Price
From $0.250 per video
Model type
image-to-video

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

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 public benchmark scores for this model yet.

Examples

Loading examples…

Related video models

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

LTX-2.3 Fast

lightricks/ltx-2.3/fast

LTX-2.3 Fast creates video from text or an image, with optional start and end frames and synchronized audio. Supports landscape and portrait output from 720p to 4K at 24, 25, 48 or 50 FPS. Choose even durations from 6 to 20 seconds; clips above 10 seconds require 720p or 1080p at 24 or 25 FPS.

LTX-2.3 Pro

lightricks/ltx-2.3/pro

LTX-2.3 Pro creates high-fidelity video from text or an image, with optional start and end frames and synchronized audio. Supports landscape and portrait output from 720p to 4K at 24, 25, 48 or 50 FPS, with 6, 8 or 10 second clips.

Gemini Omni 1.2 Flash

google/gemini-omni-flash/v1.2

Google’s video model for text prompts, image animation, up to six reference images, first-and-last-frame transitions, editing, and extension. Creates 3–15-second videos with native audio at 24 fps, from 360p to 4K. Frame transitions and extensions support 3–10 seconds; extensions can reach 30 seconds total. Uploaded-video editing and extension are unavailable in the EEA, Switzerland, and UK.

Gemini Omni 1.2 Video Upscale

google/gemini-omni-flash/v1.2/upscale

Increase the resolution of an existing MP4 video up to 15 seconds and 32 MiB. Supports 360p to 720p or 1080p, 720p to 1080p or 4K, and 1080p to 4K. Preserves aspect ratio and audio. Other source-to-target combinations are unavailable.

LongStories Story (Fast)

longstories/story-fast

Turn one idea into a finished short film: LongStories writes the story, casts the characters, draws and animates every shot, voices the narration and dialogue, adds sound effects and edits it. 30 or 60 seconds, horizontal or vertical. LongStories refuses adult and sexual content. A refused video costs nothing. A video usually takes about 30 minutes and can take over an hour. You can leave this page and come back. Every video has a small LongStories watermark and ends with a 3-second LongStories outro.

Topaz Video Colorize

topaz/video/colorize

Add color to black-and-white footage at 1080p, 2K or 4K while preserving aspect ratio. Inferred colors may differ from the original scene. Accepts readable MP4 or MOV up to 100 MiB and 15 seconds. Billing rounds measured duration up to whole seconds at 30 processing frames per second.