Instructions to use FastVideo/Matrix-Game-2.0-Base-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/Matrix-Game-2.0-Base-Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FastVideo/Matrix-Game-2.0-Base-Diffusers", 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
| { | |
| "_class_name": "UniPCMultistepScheduler", | |
| "_diffusers_version": "0.34.0.dev0", | |
| "disable_corrector": [], | |
| "dynamic_thresholding_ratio": 0.995, | |
| "final_sigmas_type": "zero", | |
| "lower_order_final": true, | |
| "num_train_timesteps": 1000, | |
| "predict_x0": true, | |
| "prediction_type": "flow_prediction", | |
| "sample_max_value": 1.0, | |
| "flow_shift": 1.0, | |
| "solver_order": 2, | |
| "solver_p": null, | |
| "solver_type": "bh2", | |
| "steps_offset": 0, | |
| "thresholding": false, | |
| "use_flow_sigmas": true, | |
| "timestep_spacing": "linspace" | |
| } |