Instructions to use Efficient-Large-Model/Open-H3-Regenerate-2K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Efficient-Large-Model/Open-H3-Regenerate-2K 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") pipe.load_lora_weights("Efficient-Large-Model/Open-H3-Regenerate-2K") 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
Commit History
Today
-
Add Open-H3-Regenerate-2K weights (#3)
- Add Open-H3-Regenerate-2K weights (a5e321e87f09aa85880b49865e6409ade54c89c1) - Remove the two LICENSE files; LMS Sharp link to the exact LoRA file (c2a37aa83037ea3829c1c292d06f8670c18fad37) - README: credit Alissonerdx for LMS Sharp (7a3529bdaeeb168384b0e74a9f3e660368dd335a) - README: License section (as StreamRender-H3), concise acknowledgements (ba8be5c3d4188aa9c7c81e67fb6f22cbc36972f9) - README: third-party components follow their own licenses (6240b6f1c2c9e0509a245a70963456e84eaabda4) - README: drop the Acknowledgements section (33b8499d1a8fe4cad9fc6376cfab5b5789787e19) - README: link the third-party components in the License section (0c65781a6578fb47ce59f1533e7be196ea1580f5) - Restore base_model/LICENSE (MiniMax H3 Community License), add NOTICE, Apache-2.0 copies for the Qwen3-VL text encoder and the latent upscaler (0c4b0aaff6d44a60d991ee6ab8a2e11edf6aaf8b) Co-authored-by: Gao Sensen <Sensen02@users.noreply.huggingface.co>5809c33
2 days ago
-
initial commit
Verified signatured8c3c3c