Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview

text-to-video model by Veda-Sparse

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Demo · Project Page· Comfy Node; · Code · Paper · Deployment Guide Don't just take our samples for it. Try your own prompts in the online demo. Available as a custom node on the Comfy Registry; see ComfyUI below. This checkpoint applies to all generation modalities supported by MiniMax-H3, including T2VA, FL2VA, and R2VA, as well as to arbitrary numbers of diffusion steps. The T2VA and 8NFE tags in the repository name only denote the training configuration and do not restrict where the predictor can be used. A dedicated R2VA fine-tuned checkpoint with further improved quality will be released in the near future. Veda is a learned sparse-attention method for video diffusion models. Attention dominates the inference cost of video diffusion, yet only a small fraction of it contributes meaningfully to the output. Veda trains a lightweight predictor, distilled from the full model, to identify the most important 10%…

Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-07T06:46:14.032Z

Inside the original model card — Document outline

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

Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview is a text-to-video model repository published by Veda-Sparse on Hugging Face. The source reports the minimax-h3 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: minimax-h3
Recent downloads (30 days): 3,694
Cumulative likes: 64
Hugging Face trending score: 28
Reported safetensors parameters: Not reported
Architecture: Not reported
License: other
Access: Not gated by Hugging Face
Created: 2026-09-25T10:56:07.000Z
Last modified: 2026-10-05T10:53:46.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: MiniMaxAI/MiniMax-H3, larryvrh/MiniMax-H3-Turbo-Lora

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.

Model card and usage instructions

Model files and configuration

Community discussion