MODEL PROFILE

Minimax-H3-R2VA-Veda-Preview

Veda-Sparse · Minimax-H3-R2VA-Veda-Preview

**Veda** is a learned sparse-attention method for video diffusion models. This checkpoint brings Veda to MiniMax-H3 reference-to-audio-video generation. It selects visual reference and generated video tiles independently; text, VLM conditioning, and audio attention remain dense. The predictor is not a LoRA and leaves the backbone weights unchanged. This preview was fine-tuned for 600 updates from the T2VA predictor on 5.17-second R2VA clips. It uses the MiniMax-H3 Turbo LoRA for eight-step generation, with up to 32 visual-reference tiles and 32 current-video tiles per query tile and head. The predictor is stored in FP8 and dequantized to BF16 when loaded. - **Learned sparse attention.** Visual reference and generated-video attention are selected independently; text, VLM conditioning, and audio stay dense. - **Fixed visual budgets.** The released preview uses 32 reference tiles and 32 current-video tiles per query tile and head. - **Plug-and-play predictor.** The FP8 predictor is separate from the H3 backbone and Turbo LoRA weights.

Video generationlicense:other
Context windowNot disclosed
Input → OutputText → Video
Model weightsNot verified
Profile updated2026/11/1 08:31:32
OVERVIEW

Model overview

**Veda** is a learned sparse-attention method for video diffusion models. This checkpoint brings Veda to MiniMax-H3 reference-to-audio-video generation. It selects visual reference and generated video tiles independently; text, VLM conditioning, and audio attention remain dense. The predictor is not a LoRA and leaves the backbone weights unchanged. This preview was fine-tuned for 600 updates from the T2VA predictor on 5.17-second R2VA clips. It uses the MiniMax-H3 Turbo LoRA for eight-step generation, with up to 32 visual-reference tiles and 32 current-video tiles per query tile and head. The predictor is stored in FP8 and dequantized to BF16 when loaded. - **Learned sparse attention.** Visual reference and generated-video attention are selected independently; text, VLM conditioning, and audio stay dense. - **Fixed visual budgets.** The released preview uses 32 reference tiles and 32 current-video tiles per query tile and head. - **Plug-and-play predictor.** The FP8 predictor is separate from the H3 backbone and Turbo LoRA weights.

Key features

特点摘要待依据来源补齐,不凭模型名称推断能力。

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
No verified prices yet. Check the source channel.

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:other。模型介绍与第三方评测均以原来源的具体版本和方法为准。