Instructions to use WaveCut/MiniMax-H3-Image-Pruned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/MiniMax-H3-Image-Pruned with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WaveCut/MiniMax-H3-Image-Pruned", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
Commit History
2 days ago
-
Card: measured one-model-at-a-time offload (72.2 s, 50.4 GiB peak) and memory modes
Verified signature7315dc5 -
Card: Hub test with stock libraries
Verified signature1c9a468 -
Load with the stock Diffusers and Transformers classes: one-hot timestep code, 51-layer text encoder
Verified signature4a14bfd -
MiniMax-H3-Image with tabulated AdaLN modulation and a 50-layer text encoder
Verified signature3a804c0