Instructions to use xfcghj/AR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xfcghj/AR with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("xfcghj/AR", 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
Download TRELLIS/trellis/modules/sparse/nonlinearity.py from xfcghj/AR: direct link, hf CLI and curl.
- Browser
- Download file 875 Bytes
-
https://huggingface.co/xfcghj/AR/resolve/main/TRELLIS/trellis/modules/sparse/nonlinearity.py
- Command line
-
hf download hf://xfcghj/AR/TRELLIS/trellis/modules/sparse/nonlinearity.py
-
curl -L -o nonlinearity.py https://huggingface.co/xfcghj/AR/resolve/main/TRELLIS/trellis/modules/sparse/nonlinearity.py
875 Bytes
| import torch | |
| import torch.nn as nn | |
| from . import SparseTensor | |
| __all__ = [ | |
| 'SparseReLU', | |
| 'SparseSiLU', | |
| 'SparseGELU', | |
| 'SparseActivation' | |
| ] | |
| class SparseReLU(nn.ReLU): | |
| def forward(self, input: SparseTensor) -> SparseTensor: | |
| return input.replace(super().forward(input.feats)) | |
| class SparseSiLU(nn.SiLU): | |
| def forward(self, input: SparseTensor) -> SparseTensor: | |
| return input.replace(super().forward(input.feats)) | |
| class SparseGELU(nn.GELU): | |
| def forward(self, input: SparseTensor) -> SparseTensor: | |
| return input.replace(super().forward(input.feats)) | |
| class SparseActivation(nn.Module): | |
| def __init__(self, activation: nn.Module): | |
| super().__init__() | |
| self.activation = activation | |
| def forward(self, input: SparseTensor) -> SparseTensor: | |
| return input.replace(self.activation(input.feats)) | |