| --- |
| license: agpl-3.0 |
| tags: |
| - image-segmentation |
| - background-removal |
| - onnx |
| - browser |
| - clip-art |
| - print-on-demand |
| - t-shirt-design |
| - birefnet |
| - knowledge-distillation |
| library_name: onnxruntime |
| pipeline_tag: image-segmentation |
| --- |
| |
| # ✂️ CrispCut — AI Background Removal for Designs |
|
|
| **Purpose-built background removal for clip art, t-shirt designs, and print-on-demand assets.** |
|
|
| Distilled from [**BiRefNet**](https://github.com/ZhengPeng7/BiRefNet) (220 M params → 6.6 M params) with **~95 % quality retention**. Exported as ONNX for browser deployment via [ONNX Runtime Web](https://onnxruntime.ai/). |
|
|
| ## Models |
|
|
| | File | Precision | Size | WASM (CPU) | WebGL (GPU) | |
| |------|-----------|------|------------|-------------| |
| | `onnx/crispcut-fast.onnx` | INT8 quantized | **6.5 MB** | ~5–10 s | ~1–2 s | |
| | `onnx/crispcut-quality.onnx` | FP32 | **25.3 MB** | ~15–25 s | ~3–6 s | |
|
|
| Both models: |
| - **Architecture:** MobileNetV2 + UNet (distilled from BiRefNet) |
| - **Trained at 1024×1024** on design-specific content |
| - ONNX opset 17 |
| - ImageNet normalisation (mean: `[0.485, 0.456, 0.406]`, std: `[0.229, 0.224, 0.225]`) |
| - Single input tensor: `input` — shape `[1, 3, 1024, 1024]` (NCHW, float32) |
| - Single output tensor: `output` — shape `[1, 1, 1024, 1024]` (logits → apply sigmoid) |
|
|
| ## Distillation Details |
|
|
| | | Teacher (BiRefNet) | Student (CrispCut) | |
| |---|---|---| |
| | Parameters | 220 M | 6.6 M | |
| | Compression | — | **33× smaller** | |
| | Quality | 100 % | ~95 % | |
|
|
| The student model uses a MobileNetV2 encoder with a UNet decoder, trained via knowledge distillation from the full BiRefNet teacher on design-specific data. |
|
|
| ## Usage with the npm package |
|
|
| ```bash |
| npm i @crispcut/background-removal |
| ``` |
|
|
| ```js |
| import { cut } from '@crispcut/background-removal'; |
| |
| // Fast mode (default) — downloads crispcut-fast.onnx from this repo |
| const result = await cut(image); |
| img.src = result.url; |
| |
| // Quality mode with GPU |
| const result = await cut(image, { model: 'quality', gpu: true }); |
| ``` |
|
|
| Models are fetched automatically from this repo at runtime. No server needed — everything runs in the browser. |
|
|
| 📦 **npm:** [@crispcut/background-removal](https://www.npmjs.com/package/@crispcut/background-removal) |
| 💻 **GitHub:** [bowespublishing/crispcut](https://github.com/bowespublishing/crispcut) |
|
|
| ## Self-hosting |
|
|
| Download the `.onnx` files from the `onnx/` folder and serve them from your own CDN: |
|
|
| ```js |
| cut(image, { modelUrl: '/models/crispcut-fast.onnx' }); |
| ``` |
|
|
| ## Training Details |
|
|
| - **Teacher:** BiRefNet (220 M parameters) |
| - **Student:** MobileNetV2 + UNet (6.6 M parameters) |
| - **Dataset:** Design-specific content (clip art, illustrations, t-shirt graphics, POD assets) |
| - **Resolution:** 1024×1024 |
| - **Distillation method:** Knowledge distillation with feature-level and output-level supervision |
| - **Fast model:** INT8 dynamic quantization (via ONNX Runtime) |
| - **Quality model:** Full FP32 precision |
|
|
| ## License |
|
|
| **AGPL-3.0** for open-source and personal use. |
|
|
| **Commercial license** required for closed-source or commercial products. |
|
|
| 📩 Contact: [bowespublishing@gmail.com](mailto:bowespublishing@gmail.com) |
|
|
