Instructions to use Perflow-Shuai/MiniMax-H3-3Step-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Perflow-Shuai/MiniMax-H3-3Step-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Perflow-Shuai/MiniMax-H3-3Step-LoRA", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Download NOTICE from Perflow-Shuai/MiniMax-H3-3Step-LoRA: direct link, hf CLI and curl.
- Browser
- Download file 571 Bytes
-
https://huggingface.co/Perflow-Shuai/MiniMax-H3-3Step-LoRA/resolve/main/NOTICE
- Command line
-
hf download hf://Perflow-Shuai/MiniMax-H3-3Step-LoRA/NOTICE
-
curl -L -o NOTICE https://huggingface.co/Perflow-Shuai/MiniMax-H3-3Step-LoRA/resolve/main/NOTICE
571 Bytes
| MiniMax H3 is licensed under the MiniMax H3 Community License Agreement, Copyright © 2026 MiniMax. All Rights Reserved. | |
| This repository provides modified MiniMax-H3 transformer weights and custom inference integration; it is not the unchanged official MiniMax-H3 base checkpoint. The transformer weights have been modified by incorporating the adapter into their projections. | |
| The inference utilities contain modified Apache-2.0 code. Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. See CODE_LICENSE for the code license. The checkpoint remains subject to LICENSE. | |