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
1. Price: huggingface.co
Open weights, free to download; self-hosted. Needs the MiniMax H3 base model.
huggingface.coNo quote yet: price is read from the official pages.
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.co3. Credit the author: huggingface.co
“on the user interface of commercial product or service that uses MiniMax H3 or MiniMax H3 Works.”
MiniMax H3
huggingface.co4. Agent access: github.com/hao-ai-lab/FastVideo
There is no package or API. Files are downloaded by hand from the official site.
github.com/hao-ai-lab/FastVideoLicense 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
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]"
Run the example script with this model and your prompt; the files download on first run.
python examples/inference/basic/basic_fasth3.py --model-path FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree --prompt "your prompt" --no-warmup --repeats 1
Mistakes to avoid
The script's default points to a different, older preview checkpoint.
The model needs that backend for the stated speed and quality.
The model's work is split across cards by its 56 attention heads.
Other sizes are not accepted.
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.
“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
“on the user interface of commercial product or service that uses MiniMax H3 or MiniMax H3 Works.” huggingface.co
“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
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
“MiniMax claims no rights over the Outputs you generate.” huggingface.co
“You may not use the MiniMax H3 Works or any of their Outputs or results to improve any other artificial intelligence model” huggingface.co
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.
- 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/)
MiniMax H3Alternatives
FastH3 4-step Preview (FastVideo) This page
Pick LTX-2 for open video with sound from text, images or audio that runs locally, for example in ComfyUI.
Pick Wan 2.2 for Apache 2.0 video models without country limits, with a 5B model for one 24 GB card.
Pick HunyuanVideo 1.5 for an 8.3B text and image to video model that runs on consumer cards.
Stable Video Diffusion (SVD-XT)
Image-to-video model that turns one still frame into a short 25-frame clip at 576x1024.
Open-source video toolkit for AI agents that clones reference videos into variants, plus a hosted multi-model video API.
Agents that do the same job
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.