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
Guys any update for H3-Regenerate-2K?
Is there any deadline or ETA you guys have for it? Also any other updates which you might want to inform us about regarding H3? Model is amazing but yeah the fast motion and other stuff is really need 2K thingy now.
The community already sorted this out to some degree. There are latent upscalers available that will take you to 2K. And even higher if you have the hardware for it.
The community already sorted this out to some degree. There are latent upscalers available that will take you to 2K. And even higher if you have the hardware for it.
I tried a lot of those but none of them worked for me, Hardware isn't issue for me, please provide me the link to the community solution you think works best, I tried Latent upscales, multi stage generation workflows and none worked for me.