AIGC
LLM chat & reasoning, text-to-image, image editing/inpainting, code generation, multimodal chat and AI content generation demos (in-browser / local server).
Cloud LLM Chat (Kimi / DeepSeek)
Chat with cloud LLMs (Kimi K3 / DeepSeek) via API — switch providers and models anytime; Kimi K3 shows its thinking first.
Code Generation & Execution
Complete code in-browser with Qwen2.5-Coder, then run Python right away via Pyodide.
Digital Human
A 3D digital human that speaks and lip-syncs. Voice via server-side Edge TTS (no download, 300+ voices) or local Kokoro (fully offline).
Image Inpainting (Moebius)
Paint over image regions to remove and inpaint them with Moebius-0.2B in-browser.
Image to 3D (TripoSR)
Generate a 3D mesh from a single image and preview it in-browser (Python backend, CPU 30-60s).
In-browser LLM Chat
LLM chat running locally in-browser via WebLLM.
Multimodal Chat (SmolVLM)
Upload images and chat multi-turn with SmolVLM-256M: charts, handwriting, scenes and objects.
Reasoning Chat (DeepSeek-R1 Distill)
Run a reasoning LLM in-browser: watch it think step-by-step, then answer (DeepSeek-R1 / MiniThinky).
Talking Photo (SadTalker)
Make a still photo talk along with audio (Python backend, non-commercial license).
Text-to-Image (Janus-Pro)
Generate images locally in-browser with Janus-Pro-1B, plus image understanding QA.
Text-to-Video (Wan2.1)
Generate short videos from text (requires GPU, limited on this machine).
WebGPU Capabilities
Inspect the browser WebGPU adapter, features and recommendations.