Minimax-h3-Turbo is an Apache-2.0-licensed video generation model distributed through Hugging Face. Developers can run it locally with Diffusers, Transformers, and Accelerate to create videos from text and image inputs.
In the Video generation space, Minimax H3 Turbo takes a focused approach. It focuses on generating and transforming videos from text or image prompts without relying on a proprietary hosted application. Minimax H3 Turbo is an open-source project aimed at developers and AI researchers. The project is open source (Apache-2.0). It runs on the command line, and it can be self-hosted.
LightX2V builds and maintains Minimax H3 Turbo, and it first shipped in 2026. The project is developed in the open on GitHub with 275 stars and 13 commits in the last 90 days. Among its 7 catalogued features are text-to-video, image-to-video, and video generation.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do