Quick Start
- Snapchat: not supported
- SPECS: partially supported
- Camera Kit Web: fully supported
- Camera Kit Mobile: fully supported
- SnapchatNot supported
- SPECSPartially supported
- Models run on device only after W8A8 quantization and conversion to Qualcomm DLC, and DLC models don't run in Lens Studio Preview
- Camera Kit WebFully supported
- Camera Kit MobileFully supported
You can get started making your own SnapML powered Lenses quickly, regardless of whether you are an ML developer, a Lens creator, or a new user.
For ML Developers
You can quickly bring in your existing neural networks into Lens Studio by dragging and dropping a compatible .ONNX or .TFLite file into the Asset Browser panel of Lens Studio.
- Checking your model compatibility
- Exporting your model for PyTorch, TensorFlow or Roboflow
- Importing and using your model
- Repository with Training Notebook Examples
- Passing in a cropped texture to your model
- Scripting how your ML is run and processed
When building for SPECS, an exported model runs on SPECS only after conversion to Qualcomm DLC. Convert it to TFLite and quantize it to W8A8 (int8 weights and activations, calibrated on 100–500 real inputs), then hand it to the SPECS developer team for the DLC conversion: Float32 ONNX → TFLite → W8A8 TFLite → DLC. DLC models don't run in Lens Studio Preview, so test on SPECS.
If you've built an ML-powered app and would like to explore leveraging Snapchat's global, highly engaged audience to drive discovery and user acquisition, please get in touch. For qualified partners, there are both no-cost organic and premium opportunities with SnapML. We look forward to hearing from you.
For Lens Creators
You can get started building a Lens using the example models provided in templates. Additionally, get started building your own model through the template guides.