534
DeepSeek-R1 WebGPU
๐ง
Next-generation reasoning model that runs locally in-browser
Generate a podcast from text, URLs, PDFs, and images
A Foundation Action Model For Generalist GUI Agents
Controlling Computers with Small Models
Detect objects in images and get bounding boxes
Select and display code snippets for various AI providers
Scalable and Versatile 3D Generation from images
Audio Conditioned LipSync with Latent Diffusion Models
Gaze detection using Moondream
Generate clickable coordinates on a screenshot