Text-to-Video
Diffusion Single File
MiniMax H3
int8
convrot
dmad
distillation
few-step
text-to-audio-video
reference-to-video
Instructions to use Spectrallic/MiniMax-H3-DMAD-int8-convrot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Spectrallic/MiniMax-H3-DMAD-int8-convrot with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download NOTICE from Spectrallic/MiniMax-H3-DMAD-int8-convrot: direct link, hf CLI and curl.
- Browser
- Download file 610 Bytes
-
https://huggingface.co/Spectrallic/MiniMax-H3-DMAD-int8-convrot/resolve/main/NOTICE
- Command line
-
hf download hf://Spectrallic/MiniMax-H3-DMAD-int8-convrot/NOTICE
-
curl -L -o NOTICE https://huggingface.co/Spectrallic/MiniMax-H3-DMAD-int8-convrot/resolve/main/NOTICE
610 Bytes
| MiniMax H3 is licensed under the MiniMax H3 Community License Agreement, Copyright © 2026 MiniMax. All Rights Reserved. | |
| This repository contains modified MiniMax H3 files: minimax_h3_fl2va_pruned_dmad_4step_int8_convrot.safetensors and minimax_h3_ref2va_pruned_dmad_4step_int8_convrot.safetensors each have the DMAD 4-step distillation LoRA merged into their weights, and minimax_h3_fl2va_pruned_dmad_8step_int8_convrot.safetensors and minimax_h3_ref2va_pruned_dmad_8step_int8_convrot.safetensors each have the DMAD 8-step distillation LoRA merged into their weights. All four are quantized to INT8 ConvRot. | |