Artifacts

A voice assistant you talk to through your microphone, with a choice of voice and language and a written transcript.

Chat demo of DeepSeek's Janus-Pro-7B, a model that can describe images and also generate them.

Writes detailed captions or training-style prompts for an image, with caption type and length options.

Chat with Cohere For AI Command models in the browser.

Turns a short persona or task description into a ready-to-use chatbot prompt.

Ask questions about images with the DeepSeek-VL2 small vision-language model.

Try a set of Qwen3-VL models on image and video questions in one place.

Describes images with the Florence-2 large and base models.

Runs a Gemma 4 model in the browser with custom WebGPU kernels, so chat needs no server.

Try chat models from several inference providers side by side with adjustable settings.

Describe or question images and videos using Qwen2-VL 7B.

Load and run GGUF language models directly in your browser without a server.

Rewrites a rough prompt into a clearer, more structured one.

Chat about images with Microsoft's Phi-3.5 Vision model.

Points your webcam at a scene and has a small vision-language model describe it continuously, locally on WebGPU.

Hosted chat with Qwen3 models, with an optional thinking mode.

Chat with Gemma 3 12B, with image input and an adjustable system prompt.

Chat playground that downloads open models and runs them locally on WebGPU with WebLLM.

Chat with a compact vision-language model about images you upload.

Runs Phi-1 and Phi-2 text generation in WebAssembly through Rust Candle with no server.

Chat demo of the efficient Gemma 3n E4B instruction model.

Runs the llama2.c small Llama model in WebAssembly with Rust Candle, generating text in the page.

Runs several vision-language captioning models, such as DeepCaption and SkyCaptioner, on your media.

Chat with the small Llama 3.2 3B Instruct model.