Extensions/ComfyUI-H3VAE_TRT
ComfyUI Extension

ComfyUI-H3VAE_TRT

Running ONNX/TRT version of the MiniMax-H3 VAE in ComfyUI, which increase speed by up to 1.7x

By lihaoyun6·Created about 12 hours ago·Updated about 12 hours ago· 1
lihaoyun6/ComfyUI-H3VAE_TRT
Nodes3
On cloudLocal install
CategoryMiniMax_H3/Acceleration
Stars1
Updatedabout 12 hours ago

Nodes (3)

MiniMax-H3 ONNX VAE Loader

The no-fuss way to run the MiniMax-H3 VAE — before you bother compiling anything

MiniMax_H3/Acceleration
MiniMax-H3 TRT Compiler

Compile the MiniMax-H3 VAE to TensorRT — the one-time job that pays for itself

MiniMax_H3/Acceleration
MiniMax-H3 TRT VAE Loader

The TensorRT MiniMax-H3 VAE loader — how your H3 videos get fast without looking like it

MiniMax_H3/Acceleration
Readme

ComfyUI-H3VAE_TRT

Running ONNX/TRT version of the MiniMax-H3 VAE in ComfyUI, which can increase speed by up to 1.7x

Preview

Installation

Install the node:

cd ComfyUI/custom_nodes
git clone https://github.com/lihaoyun6/ComfyUI-H3VAE_TRT.git
python -m pip install -r ComfyUI-H3VAE_TRT/requirements.txt

Usage

Download Models

  1. Download all 3 models -> here
  2. Put them into ComfyUI/models/vae

Nodes

  • You can run ONNX models directly, but this is usually slow. A more recommended approach is to use the MiniMax-H3 TRT Compiler node to compile ONNX into TRT Engine.
  • After successfully compiling the TRT Engines, you can use the MiniMax-H3 TRT VAE Loader node to load them.

Credits