Skip to content
ModelListedExternal
Download

RMBG 2.0 WebGPU

A WebGPU-compatible ONNX export of briaai/RMBG-2.0 background removal model, built for ONNX Runtime Web with WebGPU backend.

Sourcehuggingface.co/yamura4/RMBG-2.0-WebGPU/tree/065fd8074ef9d881d714ffaa6b215435d71b3562
KindOtherVersionRevision 065fd80Bgrade

Model source

Kind
Other
File size
349–490 MB
Version
vRevision 065fd80
Updated
Oct 9, 2026
Downloads
36
Source
Hugging Face

Source description

RMBG-2.0 — WebGPU

A WebGPU-compatible ONNX export of briaai/RMBG-2.0 background removal model, built for ONNX Runtime Web with WebGPU backend.

The Problem

The original ONNX model contains Split ops with 32 outputs (33 storage buffer bindings) and a Concat op with 1024 inputs (1025 bindings). WebGPU has a maxStorageBuffersPerShaderStage limit of 16, so the model fails at runtime with:

Uncaught (in promise) Error: MaxStorageBuffersPerShaderStage (16) exceeded. Created 33 bindings.

The Fix

Large Split and Concat ops are cascaded into trees where every node has ≤8 outputs or inputs — max 9 bindings per shader stage, well under the WebGPU limit.

BeforeAfter
50× Split(32/16 outputs)Split(4) + 4×Split(8) / Split(2) + 2×Split(8) trees
Concat(1024 inputs)4-level group-of-8 Concat tree
Concat(256 inputs)3-level group-of-8 Concat tree
Concat(64 inputs)2-level group-of-8 Concat tree
Concat(16 inputs)2-level group-of-8 Concat tree

Weights are stored as fp16 (Cast to fp32 before compute). Output is numerically identical within fp16 tolerance.

Model

FileSize
onnx/model_fp16.onnx490 MB

Usage (ONNX Runtime Web + WebGPU)

Usage (Node.js / Python ONNX Runtime)

import onnxruntime as ort
import numpy as np
from PIL import Image
from torchvision import transforms

sess = ort.InferenceSession("onnx/model_fp16.onnx")

img = Image.open("photo.jpg").convert("RGB")
transform = transforms.Compose([
    transforms.Resize((1024, 1024)),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
input_tensor = transform(img).unsqueeze(0).numpy().astype(np.float32)

alphas = sess.run(["alphas"], {"pixel_values": input_tensor})[0][0, 0]
mask = (alphas * 255).astype(np.uint8)
Image.fromarray(mask).save("mask.png")

Files

  • onnx/model_fp16.onnx — WebGPU-compatible model
  • config.json, preprocessor_config.json — model config
  • BiRefNet_config.py — custom config class (required by HF Hub)

License

CC-BY-NC-4.0 (same as briaai/RMBG-2.0).

Sources

1 source
Hugging FacePrimaryVersion 065fd8074ef9d881d714ffaa6b215435d71b3562
huggingface.co/yamura4/RMBG-2.0-WebGPU/tree/065fd8074ef9d881d714ffaa6b215435d71b3562

Verified Oct 9

Model artifacts

2 artifacts

onnx/model_fp16.onnx

onnx · 490 MB · SHA-256 79b27bf2f71a…3223 · Hugging Face

Download

onnx/model_int8.onnx

onnx · 349 MB · SHA-256 f013c94b820b…e362 · Hugging Face

Download

Source excerpts

3 excerpts
ReadmeJul 31huggingface.co/yamura4/RMBG-2.0-WebGPU

--- license: cc-by-nc-4.0 library_name: onnx pipeline_tag: image-segmentation tags: - background-removal - onnx - webgpu - remove-background --- # RMBG-2.0 — WebGPU A WebGPU-compatible ONNX export of [briaai/RMBG-2.0](https://huggingface.co/briaai/RMBG-2.0) background removal model, built for [ONNX Runtime Web](https://github.com/microsoft/onnxruntime-web) with WebGPU backend. ## The Problem The original ONNX model contains Split ops with 32 outputs (33 storage buffer bindings) and a Concat op with 1024 inputs (1025 bindings). WebGPU has a `maxStorageBuffersPerShaderStage` limit of **16**, so the model fails at runtime with: > `Uncaught (in promise) Error: MaxStorageBuffersPerShaderStage (16) exceeded. Created 33 bindings.` ## The Fix Large Split and Concat ops are cascaded into trees where every node has ≤8 outputs or inputs — max **9 bindings** per shader stage, well under the WebGPU limit. | Before | After | |---|---| | 50× Split(32/16 outputs) | Split(4) + 4×Split(8) / Split(2) + 2×Split(8) trees | | Concat(1024 inputs) | 4-level group-of-8 Concat tree | | Concat(256 inputs) | 3-level group-of-8 Concat tree | | Concat(64 inputs) | 2-level group-of-8 Concat tree | | Concat(16 inputs) | 2-level group-of-8 Concat tree | Weights are stored as fp16 (Cast to fp32 before compute). Output is numerically identical within fp16 tolerance. ## Model | File | Size | |---|---| | `onnx/model_fp16.onnx` | 490 MB | ## Usage (ONNX Runtime Web + WebGPU) ```html <script type="module"> import { InferenceSession, Tensor } from "https://cdn.jsdelivr.net/npm/onnxruntime-web@latest/dist/ort.js"; const session = await InferenceSession.create( "https://huggingface.co/yamura4/RMBG-2.0-WebGPU/resolve/main/onnx/model_fp16.onnx", { executionProviders: ["webgpu"] } ); const input = new Tensor("float32", new Float32Array(3 * 1024 * 1024), [1, 3, 1024, 1024]); const { alphas } = await session.run({ pixel_values: input }); // alphas.data is a Float32Array of shape (1, 1, 1024, 1024) </script> ``` ## Usage (Node.js / Python ONNX Runtime) ```python import onnxruntime as ort import numpy as np from PIL import Image from torchvision import transforms sess = ort.InferenceSession("onnx/model_fp16.onnx") img = Image.open("photo.jpg").convert("RGB") transform = transforms.Compose([ transforms.Resize((1024, 1024)), transforms.ToTensor(), transforms.Normalize([0.485, 0.456...

NoteOct 9huggingface.co/yamura4/RMBG-2.0-WebGPU

Source context: 36 downloads · 4 likes · Pipeline image-segmentation · Library onnx · Repo yamura4/RMBG-2.0-WebGPU

NoteJul 31huggingface.co/yamura4/RMBG-2.0-WebGPU

Source context: 235 downloads · 4 likes · Pipeline image-segmentation · Library onnx · Repo yamura4/RMBG-2.0-WebGPU