Instructions to use Wattsey/birefnet-lite-512-webgpu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use Wattsey/birefnet-lite-512-webgpu with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-segmentation', 'Wattsey/birefnet-lite-512-webgpu');
BiRefNet_lite 512 (WebGPU)
BiRefNet_lite (MIT, by ZhengPeng7) at 512x512, fp16 ONNX, from studioludens/birefnet-lite-512.
The graph is rewritten so it runs fully on WebGPU within phone GPU limits: deformable-conv
GatherND nodes and wide Split nodes are replaced with equivalent ops using the MIT patch
scripts from jiabins0303/birefnet-lite-1024-webgpu. Output is bit-identical to the original.
- Downloads last month
- 66
Model tree for Wattsey/birefnet-lite-512-webgpu
Base model
ZhengPeng7/BiRefNet_lite