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
Upload 2 files
A high-end retro 80s commercial product shot, inspired by classic Coca-Cola and Pepsi commercials. The main subject is the welding torch [attached image], perfectly preserving its original shape, color, and texture without any modifications. The torch is placed in a static industrial welding workshop environment. Background details: blurred heavy metal structures, welding machines, welding masks, spools of welding wire, and barrels of welding wire. No humans, no people, no hands. The torch is the hero, gleaming under dramatic studio lighting. Aesthetic: VHS tape effect, slight grain, neon blue and orange rim lighting, lens flares, synthwave atmosphere, dynamic camera movement zooming in slowly on the torch as if it is a precious artifact. High contrast, glossy, memorable, cinematic.