Deploying ML models to mobile devices
summary
Builds an Android image‑generator app that runs a diffusion model locally using MediaPipe’s Image Generator, with conversion scripts and sample code on Google’s GitHub. Uses models matching Stable Diffusion v1.5 and accepts LoRA weights from Vertex AI Model Garden. Generation runs synchronously on a background thread, with a default of 20 iterations and optional display every 5 steps (4 intermediate images), and the workflow recommends Android Studio Giraffe and a device with ~8 GB RAM to run successfully.
AI-written summary · about
chapters (6)
related talks
40mOn-Device Machine Learning for Android with MediaPipe
32mAdvanced on-device ML made easy
01h 01mHow to Optimize, Validate and Deploy ML Models on Device
39mMachine Learning on Android Demystified
42mOn-Device Machine Learning with Google AI Edge
20mTraining a foundation image model and deploying it to millions of users
15mEmbed Your Machine Learning Model in Your App?
39mCreating smaller, faster, production-worthy mobile machine learning models for Android