Model reference · open weights
FastVideo-FastH3-8-Step is an open-weight video model from FastVideo. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | FastVideo |
|---|---|
| Type | Video models |
| Task | Text→video |
| Parameters (lead) | 35.0B |
| Runs with | diffusers |
| Based on | MiniMaxAI/MiniMax-H3 |
| Released | 2026-09-04 |
| Popularity | 2 downloads / month |
| Licence | Commercial licence needed |
About
The FastH3 8-Step V2 checkpoint from FastVideo. It generates synchronized video and audio from text with eight transformer forwards. This step-1300 model was trained with data-free DMD2 and VSA-H3 at 80% sparsity.
This checkpoint requires FastVideo's VSA-H3 attention backend. Its video scheduler shift is 10, not the base model's 12; use the example below, which reads the trained schedule from the checkpoint.
Install uv, then use the CUDA 13 / Blackwell path below. It selects FastVideo's published CUDA kernel wheel instead of compiling the kernel locally. See the installation guide for other platforms.
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]"
python examples/inference/basic/basic_fasth3_8step.py \
--prompt "your prompt" \
--no-warmup \
--repeats 1
The tested defaults use four B200 GPUs and the trained eight-forward schedule.
On other multi-GPU CUDA systems, follow the installation guide and add
--no-replicated-dit --vsa-kernel triton --no-fa4. The GPU count must divide
H3's 56 attention heads.
This checkpoint supports text-to-audio-video generation. FL2VA and Ref2VA were not distilled. Difficult motion, fine detail, and some audio may remain below the base MiniMax H3 model. This checkpoint inherits the MiniMax H3 Community License.
We thank Nuva Lab for bringing production grounding to FastH3 through its experience with real-world creative video-agent workloads. Its production-aligned post-training insights help bridge open-source research to practical data-assisted distillation for commercial video workflows, with Omni Ref as the next focus.
We thank the NVIDIA FastGen team for the DMD2 framework and H3 reference experiment that helped us align the score clock, modality shifts, and backward simulation.
We also thank MiniMax for releasing H3-Base, and the vLLM project, NVIDIA, and MBZUAI for their continued sponsorship and support of FastVideo.
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys fastvideo-fasth3-8-step for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (fastvideo-fasth3-8-step below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/videos/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"fastvideo-fasth3-8-step","prompt":"a drone shot over a forest"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.