OpenVDN/vdn-minimax-h3
text-to-video model by OpenVDN
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
[📄 Paper] [Blog] [Code] [🤗 Weights] [ModelScope] [Local Inference] [License] We release VDN-Minimax-H3 (VDN-H3), a hybrid-attention model that generates video faster than it plays, powered by MiniMax H3. It offers these key features: This repository holds the weights. Read the Blog for the architecture, training method, benchmarks, and qualitative results. The inference and training code, together with the setup instructions, is available at OpenVDN/vdn-minimax-h3. Before you begin, please read the license before downloading or running VDN-H3. The quickest way to a first render is using diffusers, as we already release the checkpoints as modular diffusers components: numinferencesteps counts sigma grid points, so 9 of them is 8 model evaluations. inferdiffusers.py runs the same as a script, keyframes included. On a 24 GB card, stream the transformer in one block at a time: swap pipe.transformer.to("cuda") for the line below, or add --offloaddit to the script. 345 frames then peak at 22…
Read the full model card ↗ · Preview checked 2026-10-30T14:09:48.971Z
Inside the original model card — Document outline
- Video DeltaNet: Hybrid Attention to Speed Up Video Models with Near-Lossless Quality
- News
- Set up the environment
- Inference with Diffusers
- Inference with SGLang
- Inference with our repository
- Download the weights
- Render a video
- Use your own prompt
- Supporting FL2VA, I2VA, and L2VA
- Choosing an inference configuration
- Results
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
OpenVDN/vdn-minimax-h3 is a text-to-video model repository published by OpenVDN on Hugging Face. The source reports the diffusers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-video
- Library
- diffusers
- Recent downloads (30 days)
- 342
- Cumulative likes
- 303
- Hugging Face trending score
- 67
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-09-02T05:03:41.000Z
- Last modified
- 2026-09-11T22:15:40.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: MiniMaxAI/MiniMax-H3
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-15T06:34:02.617Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
QuantStack/Wan2.2-TI2V-5B-GGUF
QuantStack/Wan2.2-T2V-A14B-GGUF