Instructions to use diffusers-modular/minimax-h3-inpainting with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use diffusers-modular/minimax-h3-inpainting with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("diffusers-modular/minimax-h3-inpainting", 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
Commit History
14 days ago
-
Update strip example to k5 harmonize output
Verified signatureb2689ca -
Update strip example to k5 harmonize output
Verified signature3e8c3b7 -
Document mask_drop_step single-pass harmonize
Verified signaturec6add68 -
Add mask_drop_step for single-pass harmonize
Verified signature4f01ac3
15 days ago
-
Upload README.md with huggingface_hub
Verified signature3af1c47 -
Upload assets/strip_example.mp4 with huggingface_hub
Verified signature52f0a6d -
Upload assets/strip_example.webp with huggingface_hub
Verified signature11064b3
-
Update README.md
Verified signature09e555a -
Update README.md
Verified signatureb12ef69 -
Update README.md
Verified signature9b67634 -
Update minimax_h3_inpaint_blocks.py
Verified signatureec6e9ca
-
Masked video+audio inpainting blocks for MiniMax-H3
Verified signaturedca1cd6 -
initial commit
Verified signatureb02a286