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
Any ETA for H3.1?
Hi, the MiniMax team!
Glad to see you stay dedicated to the Open-Weight ecosystem despite everything (and after LTX faking the likes I lost the respect for them).
I saw your recently released H3-Image and it's very good on surreal concepts. Now there are 4 months after the release of H3 in August. I think I saw information on that the H3.1 release is going to take place before the end of the year? Might this be true? It would be a decent Christmas / New Year gift for all.
I wonder if H3.1 will come even before LTX-3 and Flux-3 video open, because those models are too delayed and honestly they quite deserve it because of their views on censorship and aesthetics.
Thank you! Even if you won't answer.
Like really, only you and Kandinsky, and PAN stay for now. All the others have offed themselves