Everything in the catalog

Generate realistic images in pixel space

Переехали на code.gpt-chatbot.ru

One image to a 3D object (Gaussian splats)

Estimate depth, surface normals and albedo maps from a single photo.

Demo of the Qwen 3.5 Multimodal Model

Collection of Qwen-Image-2.1 LoRAs — Plug and Play

Classifies photos of pizza, steak and sushi.

Translates spoken audio into another language and speaks the result.

Try Xing4.0-29B-A4B using this hosted demo.

Detect text blocks, tables, figures and other layout regions on document page images.

Open-source AI note-taker that produces notes from your sources and cites where each point comes from.

Draw a box and remove the designs, objects, and accessories.

Writes a movie plot from a poster image.

Super-resolution of images with SwinIR.

Classifies anime-style images into categories.

Estimates whether pasted text was machine-generated using an adversarially trained detector.

On-device decisions from camera and microphone

Rewrites AI drafts so they read like a person wrote them while keeping the facts.

AI image upscaler for enlarging pictures.

Masks the clothing area and overlays a new garment on a person photo.

Paints a photo in the style of an artwork.

Edit images with Qwen Image Edit 2511 in just four steps using a lightning-speed setup.

IBM Granite speech recognition running locally through WebGPU in the browser.

Converts text to speech in the browser using small local text-to-waveform models of 3.96M and 9.36M parameters.