MiniMax H3 adds open weights, stereo audio and 15-second 2K video generation
petrusenko_max · x · 2026-08-04
MiniMax H3 is launched with open weights and native stereo audio. The model can generate up to 15-second 2K video clips from text, images, video, or audio inputs in a single pass.
The post also says H3 is natively supported in ComfyUI and can run locally on an Nvidia 3060, making it notable both as a multimodal generation model and as a relatively accessible local workflow option.
More from Infra
- Databricks reaches a $4B revenue run-rate and nearly $21.8B raised, says Infra Play — thedealdirector · 2026-08-04
- AI index steepens 5x after late 2024 as compute shifts from pretraining to inference — ProfBuehlerMIT · 2026-08-04
- Local Benchmarking of DeepSeek V4 Flash Quantizations: Q3 vs Q8 — Spicy_mch4ggis · 2026-08-04
- Bittensor’s Root Reborn revives validators and removes automatic sell pressure — const_reborn · 2026-08-04
- ARPL makes llama.cpp adapt to ARM ISA and core topology at runtime — OpeningTough145 · 2026-08-04
- DeepSeek V4 Flash 0731 hits a ctx_other error in llama.cpp speculative decoding — Ambitious_Fold_2874 · 2026-08-04