Model · Video

MAGI-1

A free, open video model from Sand AI that animates a photo, continues an existing clip or makes video from a description, building it chunk by chunk. The small version needs a 24 GB graphics card; the large one needs data-centre hardware.

Go to MAGI-1’s website

At a glance

Open or closed
Fully open
Weights and code downloadable under a standard open licence
Apache 2.0.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence
Apache 2.0 (Permissive (e.g. Apache 2.0, MIT))
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?
Yes
Apache 2.0 allows commercial use; the card has no separate statement about outputs.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Cost
Free option: Free to download and run yourself
Plans below.
How you use it
On your own computer, In your browser
web_app = Sand AI's own site linked from the card (not checked). No HF inference provider deploys it; ComfyUI integration exists.
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed
Technical
Our judgement.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by
Sand AI
No address or country stated on the model card.
source · checked 12 Oct 2026 · checked on the maker's own page
Status
Available
Latest news on the card is from May 2025 (ComfyUI support, 4.5B distill release).
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

What you can make with it

image to videotext to videovideo to video

Pipeline tag is image-to-video; card also lists text-to-video and video-to-video (continuing a prefix video).
source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

No paid plans listed.

Sand AI also runs a hosted app at magi.sand.ai; its pricing was not checked.
source · checked 12 Oct 2026 · checked on the maker's own page

Related

Where you can run it

Hugging Face

Other options for “A video, by bringing a photo to life”

Adobe Firefly, Akool, Artbreeder, Claid, CogVideoX, ComfyUI, Creatify, DeeVid AI, DomoAI, Draw Things, Dreamina, Dzine, EchoMimic, fal, Filmora, Flair, Fotor, getimg.ai, Google Flow, Hailuo AI, Higgsfield, HitPaw VikPea, Ideogram, ImagineArt

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.