MiniMax H3 Max tops video leaderboards with native audio support
gorkem · x · 2026-08-28
MiniMax H3 Max, a post-trained variant of MiniMax H3 built and served by fal, is now available via API.
Performance:
- Debuts at #1 in Image-to-Video with Audio and #3 in Text-to-Video with Audio on the Artificial Analysis Video Leaderboards.
- Outperforms the base MiniMax H3 and ByteDance's Dreamina Seedance 2.0 in the Image-to-Video category.
Features:
- Tuned for stronger prompt adherence and better aesthetics.
- Co-optimized with fal's custom inference stack for higher throughput.
- Generates 5 to 15-second clips with native audio at up to 768p resolution.
Related event: fal's H3 Max: Post-trained MiniMax H3 Tops Image-to-Video Leaderboards(29 posts)→
More from Multimodal
- Snap Spectacles + Gemini 4 Argon demo designs LEGO builds from your brick pile — stspanho · 2026-10-16
- Stanford paper: generative representation learning cuts tokenizer training compute by 7-8x — HirokatuKataoka · 2026-10-16
- UniForge3D open-sourced: joint 3D reconstruction and generation from sparse unposed views — camenduru · 2026-10-16
- Seedance 2.5 Pricing Varies Up to 3-4x Across Providers — videorouter · 2026-10-16
- Seedance 2.5 demo: collapsing-city disaster chase with the prompt shared — umesh_ai · 2026-10-16
- Flying car demo: Grok Imagine image + Minimax H3 video generation — creatoroff · 2026-10-16