InEngineering @ Draw ThingsbyLiu Liu·Apr 30, 2025BF16 and Image Generation ModelsDraw Things maintains its own local inference and training stack for image generation models. We support diffusion transformer models…
InEngineering @ Draw ThingsbyLiu Liu·Jan 7, 2025Metal FlashAttention 2.0: Pushing Forward On-Device Inference & Training on Apple SiliconMetal FlashAttention underpins Draw Things’ claim of fastest image generation inside the Apple ecosystem. It conserves system memory, it is…A response icon1A response icon1
InEngineering @ Draw ThingsbyLiu Liu·Jun 24, 2024From iPhone, iPad to Mac — Enabling Rapid Local Deployment of SD3 Medium with s4nncSD3 Medium was released on June 12th, 2024. Like everyone else, we gained access to the model on the same day. From then on, it is a race…A response icon4A response icon4
InEngineering @ Draw ThingsbyLiu Liu·Oct 5, 2023Draw Things Democratizes Local Large Model Fine-tuning on iPhone, iPad and MacLarge language models and image generation models currently require hundreds of thousands to tens of millions of dollars for hardware…
InEngineering @ Draw ThingsbyLiu Liu·Aug 9, 2023Integrating Metal FlashAttention: Accelerating the Heart of Image Generation in the Apple EcosystemDraw Things was the first practical app to run full-blown image generation models at the “edge” — directly on your mobile phone. Since its…