A quantized Minimax-H3 model checkpoint for local multimodal generation, including text-to-video, image-to-video, video-to-video, and text-to-audio-video workflows. It is intended for developers and AI practitioners using Diffusers, ComfyUI, or compatible local inference environments.
In the Other AI space, Minimax H3 Nvfp4 INT4 INT8 Convrot takes a focused approach. It focuses on running a quantized multimodal generation model locally without relying on a hosted inference service. Minimax H3 Nvfp4 INT4 INT8 Convrot is an open-source project aimed at AI developers and machine learning practitioners. The project is open source (Open Source). It ships for the command line, and it can be self-hosted.
It is developed by Abiray. Key capabilities include text-to-video, image-to-video, and video-to-video.
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