Instructions to use Skywork/Matrix-Game-3.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Skywork/Matrix-Game-3.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Skywork/Matrix-Game-3.0", 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
Improve model card metadata and content
#1
by nielsr HF Staff - opened
Hi! I'm Niels from the Hugging Face community team.
I've opened this PR to improve the model card for Matrix-Game 3.0. Specifically, I have:
- Added the
library_name: diffuserstag based on the presence ofmodel_index.jsonand Diffusers versioning in the config files. - Updated the
pipeline_tagtotext-to-videofor better discoverability. - Linked the model to its research paper on the Hugging Face Hub.
- Added a "Quick Start" section with installation and inference instructions sourced from the official GitHub repository.
These changes will help users find and use your model more effectively!