Multimodal model

MiniMax H3

MiniMax H3 is a general purpose omni modal generation model that jointly understands multimodal context spanning text, images, video, and audio. It generates video with native stereo audio at up to 2K resolution and 15 seconds in length, and supports unified reference and editing across images, video, and audio expressed through natural language rather than fixed task types.

Type
Multimodal
Weights
Open
Downloads
3.7M
Likes
5.7k
Pipeline
image text to video
License
other

Model hub

MiniMaxAI/MiniMax-H3

Repo
MiniMaxAI/MiniMax-H3
Library
minimax-h3
Access
Public
Technical tags and languages
minimax-h3 diffusers safetensors text-to-video image-to-video image-text-to-video video-to-video text-to-audio-video image-to-audio-video image-text-to-audio-video video-to-audio-video audio-to-audio-video
Open on Hugging Face

Related tools

10

More from MiniMax

14

About MiniMax

1

MiniMax develops multimodal foundation models and AI products for text, speech, music, images, and video.

Tools using MiniMax H3

40