Instructions to use MiniMaxAI/MiniMax-H3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MiniMaxAI/MiniMax-H3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-H3", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
Getting different Accents when speaking the same language
In my generations, all of the characters speak English, but they are not all American. I can get Minimax to give some British accents for English dialogue, but if I ask for a non-native accent to speak an English phrase, it reverts to an American accent. I have tried:
She says in a French accent "" - Get American accents
She says in English with a strong French accent "" - Get American accents; sometimes it translates to French
She says in an Australian accent "" - Get Australian accents
Has anyone else tried this? I have a character that is a French spy, so it is important that she uses a French accent in English
Any help would be welcome.
I am using Image to Video with just a first frame. I would prefer not to have to use Reference to Video, as I have specific start points