---
title: "MAGI-1"
description: "MAGI-1 from Sand AI: image-to-video and video-generation; Runner parity pending; dedicated `magi-official-cu124`."
modelId: "magi-1"
pageSource: authored
---

MAGI-1 is Sand AI's open autoregressive video generation model, cataloged for image-to-video and general video generation and tracked as a high-priority open candidate with Apache-2.0 HF metadata. The WorldFoundry route is complete and reports missing checkpoint assets at runtime.

<ModelPaperFigures modelId="magi-1" locale="en" />

The recorded paper is [arXiv 2505.13211](https://arxiv.org/abs/2505.13211).

Code: [SandAI-org/MAGI-1](https://github.com/SandAI-org/MAGI-1).

<ModelCommandBuilder modelId="magi-1" locale="en" />

## What it is for

`magi-1` is the recorded text/image-to-video line. Use it when you want both prompt and still conditioning on the same catalog card.

Upstream describes MAGI-1 as a large autoregressive video model generating chunk-by-chunk with causal attention, enabling streaming-style continuation. This repository records only the prompt+image input contract and the generated_video artifact; scale and internals are not recorded here.

Catalog tasks include image-to-video and video-generation. Documented modalities: image in, video out.

Recorded evaluation entry points include [VBench](/docs/evaluation/benchmark-hub/vbench) (Baseline video generation quality suite).

## Runtime contract

Optional `prompt`, `negative_prompt`, `input_path`, `frames`, and `fps`; artifacts `magi-1.mp4`.

CLI task profiles: `interactive-video`. WorldFoundry binds `MAGI1Pipeline`.

Family status: **Runner parity pending**.

No runner-parity record exists yet — treat GPU validation as not done. Stage the MAGI-1 weights first; the route fails informatively when they are missing.

Added as a high-priority open video generation candidate with Apache-2.0 HF metadata.

The in-tree MAGI-1 I2V route is wired with the official example image/config assets, local sand-ai/MAGI-1 checkpoint, 4.5B distill profile, sampling controls, fps, and seed.

## Running in WorldFoundry

Launch `worldfoundry-eval run magi-1 --pipeline.task-profile interactive-video` to sample the clip. The command builder above switches `--pipeline.task-profile` among recorded tasks and still emits `worldfoundry-eval run`.

It runs in the dedicated environment `magi-official-cu124` (Python 3.10.12, CUDA 12.4).

Recorded weight repositories include `sand-ai/MAGI-1` and `sand-ai/MAGI-1`. Prepare the environment and check local assets with `bash scripts/inference/prepare_model_infer.sh magi-1`. Add `--download` to fetch missing public checkpoints.

Recorded licenses include apache-2.0; status: **Runner parity pending**.

<ModelRelatedRecipes modelId="magi-1" locale="en" />