This Hugging Face repository provides a fused, INT8-quantized MiniMax H3 diffusion model for image-to-video generation. It is intended for local inference workflows, including ComfyUI and other compatible diffusion tooling.
In the Other AI space, Minimax H3 Fused Turbo Int8 Convrot takes a focused approach. It focuses on running a quantized MiniMax H3 image-to-video model locally with reduced hardware requirements. It is built as an open-source project for AI developers and local video-generation users. Minimax H3 Fused Turbo Int8 Convrot is available on the web and the command line, and it can be self-hosted.
MATLOWAI builds and maintains Minimax H3 Fused Turbo Int8 Convrot, and it first shipped in 2023. Development happens publicly on GitHub with 293 stars and 735 commits in the last 90 days. Among its 5 catalogued features are image-to-video generation, INT8 quantization, and turbo inference.
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