Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

FastH3 4-step Preview (FastVideo)

by FastVideo (Hao AI Lab)

Four-step distilled MiniMax H3 checkpoint that generates synchronized video and audio from text.

AI video generators and platforms Open source

GitHub repoWebsite

2. Commercial use: huggingface.co

“You may not use, reproduce, modify, distribute, or display the MiniMax H3 Works or any of their Outputs or results outside the Applicable Territory.”

Allowed only outside the EU, UK, South Korea and USA, with "MiniMax H3" shown in the interface and authorization above 20 million USD revenue.

huggingface.co

License checked Oct 27, 2026 against 1 official page. Tap a verdict to see its source. How we checked Report an error

FastH3 Preview: fast open model for video with sound

FastH3 Preview is an open AI model from the FastVideo team that makes a short video with matching sound, such as voices and noises, from a written description. It is a sped-up version of MiniMax's H3 video model and needs very powerful data-center graphics cards. Its license does not allow any use in the European Union, the United Kingdom, South Korea or the United States.

Where you can use it

A clip with sound from text

Describe a scene, the camera and the sounds, and get one video where the picture, speech and noises fit together.

Vertical and square videos

Make the same kind of clip upright for phone stories, square for a feed, or wide for a website, by setting the size.

Run on other multi-card servers

On a rented server with several NVIDIA cards that are not B200, switch the fast attention parts to the general versions.

Download only the small adapter

If you already have the base H3 model, take only the small speed-up add-on instead of all the files again.

Train your own faster video model

Teams that build video models can use the same FastVideo toolkit to fine-tune and speed up other open video models.

Explainer clips with narration Idea

Make short how-to or product clips where the narrator's voice and the on-screen action match, for teams inside the allowed countries.

As reported by FastVideo (Hao AI Lab): FastH3 makes a 15 s 768p video in under 13 s on 8 B200 cards.; Up to 14x speedup on a single NVIDIA Blackwell card..

FastH3 4-step Preview (FastVideo) popularity

25 / 100
Gid Score, same scale as developer tools
4,829
GitHub stars
FastH3 4-step Preview (FastVideo): GitHub starshao-ai-lab/FastVideo 4,829

How the Gid Score is calculated

How to start

Tell your AI assistant

“Only if I am outside the EU, UK, South Korea and the USA, on my 4-GPU Blackwell server install FastVideo with the fasth3 extras and run basic_fasth3.py with --model-path FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree, my prompt, --no-warmup --repeats 1.”

Show codeStep 1 or Step 2

Get the FastVideo code and install it with its FastH3 extras in a fresh Python 3.12 environment (path for CUDA 13 and Blackwell cards).

git clone https://github.com/hao-ai-lab/FastVideo.git
cd FastVideo
uv venv --python 3.12 --seed
source .venv/bin/activate
UV_TORCH_BACKEND=cu130 uv pip install \
  --no-sources-package fastvideo-kernel \
  -e ".[fasth3]"

Mistakes to avoid

running basic_fasth3.py without --model-path
always pass --model-path FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree

The script's default points to a different, older preview checkpoint.

swapping in a standard attention backend to avoid installing the VSA kernel
install FastVideo's VSA-H3 backend and kernel

The model needs that backend for the stated speed and quality.

--num-gpus 3, 5 or 6
use a card count that divides 56, such as 2, 4, 7 or 8

The model's work is split across cards by its 56 attention heads.

--height 720 --width 1280
sizes in multiples of 32, such as 768 by 1344

Other sizes are not accepted.

setting it up for a person or company in the EU, UK, South Korea or USA
stop and pick a model without territory limits, such as Wan 2.2

The license does not allow any use there, outputs included.

License

MiniMax H3 Community License Agreement. Under the MiniMax H3 Community License you may use it, also commercially, only outside the EU, UK, South Korea and the USA. Paid products must show "MiniMax H3" in their interface, and outputs may not train other AI models.

Commercial use
With conditions

“You may not use, reproduce, modify, distribute, or display the MiniMax H3 Works or any of their Outputs or results outside the Applicable Territory.” huggingface.co

Credit
Required

“on the user interface of commercial product or service that uses MiniMax H3 or MiniMax H3 Works.” huggingface.co

Inside your app or game
With conditions

“you must, before making that product or service available and throughout its operation, implement, maintain, test, and periodically review reasonable and proportionate technical and organizational safeguards” huggingface.co

Pass the files on to your users
With conditions

Allowed inside the territory with the license copy, notices on changed files and the NOTICE text file.

“You must cause any modified files to carry prominent notices stating that you have modified such files;” huggingface.co

Monetized YouTube
With conditions

“MiniMax claims no rights over the Outputs you generate.” huggingface.co

AI training
Banned by the terms

“You may not use the MiniMax H3 Works or any of their Outputs or results to improve any other artificial intelligence model” huggingface.co

Bots and bulk downloads
Not stated

AllowedWith conditionsNot allowedNot stated or not checked yet

Is FastH3 4-step Preview (FastVideo) free for commercial use? The full answer Not legal advice. Check the license page before you ship.

For your agent

License rules tell your agent what it may do with FastH3 4-step Preview (FastVideo). Paste them into your prompt or AGENTS.md.

License rules
- FastH3 4-step Preview (FastVideo) (AI video generators and platforms). Four-step distilled MiniMax H3 checkpoint that generates synchronized video and audio from text. Price: free; commercial use with conditions; credit required; ship inside your app with conditions; no AI training on its content.
  Connect: download from https://huggingface.co/FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree (no API).
  Rule: Use is allowed only inside the Applicable Territory: it excludes the EU, UK, South Korea and the USA.
  Rule: Show "MiniMax H3" in the interface of commercial products; ask MiniMax for a license above 20 million USD yearly revenue.
  Rule: Do not use the weights or their outputs to train or improve another AI model.
  Rule: Hosting generation for third parties needs safeguards under the Acceptable Use Policy.
  License: https://huggingface.co/FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree/blob/main/LICENSE (checked 2026-10-27; details: https://agentgid.com/assets/fastvideo/)
Can an agent use it by itself?
No.
API, key or account
Not needed. Everything runs on your side.
MCP server
None found
Credit line, if you want one
MiniMax H3
This card for machines

Alternatives

FastH3 4-step Preview (FastVideo) This page

Free With conditions Download

LTX-2 (LTX-2.5)

Pick LTX-2 for open video with sound from text, images or audio that runs locally, for example in ComfyUI.

Free With conditions Download

Wan 2.2

Pick Wan 2.2 for Apache 2.0 video models without country limits, with a 5B model for one 24 GB card.

Free Commercial OK Download

HunyuanVideo 1.5

Pick HunyuanVideo 1.5 for an 8.3B text and image to video model that runs on consumer cards.

Free With conditions Download

Stable Video Diffusion (SVD-XT)

Image-to-video model that turns one still frame into a short 25-frame clip at 576x1024.

Free With conditions Download

Hypit

Open-source video toolkit for AI agents that clones reference videos into variants, plus a hosted multi-model video API.

Free tier With conditions API, npm

All ai video generators and platforms

Agents that do the same job

video editing agent skill, open source, 31.3K GitHub stars
AI video creation platform, open source, 22.2K GitHub stars
agent skill, open source, 22K GitHub stars
agent skill, open source, 21.2K GitHub stars
agent, open source, 6,968 GitHub stars

From AgentGid's agent catalog, not yet checked as asset sources: their license and price are on their agent pages.

Questions

Can I use it from Germany, the UK or the USA?

No. The license does not apply in the EU, the UK, South Korea or the USA; MiniMax invites people there to ask about a separate license.

Who owns the videos I make?

MiniMax claims no rights over them; you and your users are responsible for them and their use.

Can it start from my own picture?

Not this preview; it supports text to video with sound only.

Does it run on one home graphics card?

The tested setup is four B200 data-center cards; on other multi-card systems the card count must divide 56.