Instructions to use DeepBeepMeep/MiniMax-H3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use DeepBeepMeep/MiniMax-H3 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 loras/ptd_refasymopd/NOTICE from DeepBeepMeep/MiniMax-H3: direct link, hf CLI and curl.
- Browser
- Download file 574 Bytes
-
https://huggingface.co/DeepBeepMeep/MiniMax-H3/resolve/main/loras/ptd_refasymopd/NOTICE
- Command line
-
hf download hf://DeepBeepMeep/MiniMax-H3/loras/ptd_refasymopd/NOTICE
-
curl -L -o NOTICE https://huggingface.co/DeepBeepMeep/MiniMax-H3/resolve/main/loras/ptd_refasymopd/NOTICE
574 Bytes
| MiniMax H3 is licensed under the MiniMax H3 Community License Agreement, Copyright © 2026 MiniMax. All Rights Reserved. | |
| PTD RefAsymOPD adapters: taobao-content-ai. | |
| Source: https://huggingface.co/taobao-content-ai/MiniMax-H3-PTD-RefAsymOPD-LoRAs | |
| Source revision: 5501eb8918ef8bcb858ff045b885bf47a2c4502b | |
| These weights have been modified for WanGP inference: the eight-hop adapter stack was split into scheduled LoRAs, SwiGLU factors were reordered, and the output heads were converted to the existing FP32 base/relative-head representation. No new training was performed. | |