Everything in the catalog

Parses text, tables and formulas from document images with PaddleOCR-VL.

Edit a Jinja chat template and preview how it formats a conversation into model input text.

Makes passport and ID photos from a portrait: removes the background, crops to size and sets the backdrop color.

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

Translates text between a large set of languages with Meta's NLLB model.

Background removal demo using the InSPyReNet model through the rembg tool.

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

Extract text from complex documents and images with a multimodal OCR model.

Split an audio file into separate dialogue, music, effects and individual speaker tracks.

Video tool that makes clips from text or from an image and can extend an existing video.

Colorizes a grayscale picture, steered by a text prompt describing the colors you want.

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

Edit images with Qwen Image Edit 2509 using a selection of LoRA adapters.

Edit a picture by typing an instruction; Qwen-Image-Edit rewrites the image to match.

Converts a Hugging Face model to Apple MLX format and uploads it to your account; needs login.

Erases text from images, in any language, and fills the gap to leave a clean picture.

Swaps faces or whole heads between images using a Flux.2 Klein based model.

Text-to-image demo for Qwen-Image, a model known for rendering readable text inside pictures.

Pulls out named entities from text using labels you type in, with no training.

Voice cloning text-to-speech that supports more than 600 languages.

Places a logo onto any image or product mockup scene.

Converts a document page image into structured Docling markup using a 258M model run in the browser.

Chat with a PDF from an upload or URL; you provide your own OpenAI API key.

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