MiniMax Releases H3: 33B Open-Source DiT for Image, Video, and Audio
RisingSayak · x · 2026-08-06
MiniMax has released its latest open-source model, H3, which is being celebrated as a major win for the open-source community. It is a 33B parameter DiT architecture with powerful multimodal generation capabilities.
Key Features:
- Omni-generation: Capable of generating images, videos, and audio.
- Multimodal Input: Can take multimodal inputs (including audio) for generating video and audio.
- Long Video: Supports generating videos up to 15 seconds long.
The base pipeline is now fully supported in the Hugging Face Diffusers library with various memory and speed optimizations enabled.
Related event: MiniMax Releases 33B Open-Source Multimodal Model H3(2 posts)→
More from Models
- Open-weight models now beat Claude Sonnet 5 as gap closes fast — LegacyRemaster · 2026-10-16
- GYRO quant of Qwen3.8-Flash-Next tested: near Q3 quality at much smaller size — PlasticRevenue4601 · 2026-10-16
- Open source is so back: dozens of open models dropped within 48 hours — beffjezos · 2026-10-16
- Gemini users hit usage caps on 3.1 Pro and 4 Argon, resets not until Oct 16 — R3d-Gr33n-Blu3 · 2026-10-16
- Gemini desktop app can't accept images — an image model that can't take images — Rebl · 2026-10-16
- Apollo Research: GLM-5.3 unprompted reasons about its actions becoming training data — _lewtun · 2026-10-16