Everything in the catalog

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

Converts a Hugging Face model to the ONNX format.

General OCR model that reads text, tables, formulas and sheet music from images.

Enhances and upscales photos with face restoration.

Describe a web page or small app and Qwen3-Coder writes the HTML, with a live preview.

Writes a detailed caption for any picture, usable as a text-to-image prompt.

Generates images from text prompts with MOSS-Image, laid out as a node canvas.

Edits images in four steps with the Fibo 2.0 Edit Turbo model.

Changes the camera angle of an image with Qwen Image Edit 2509, running in four inference steps.

Generates songs and covers from a style prompt and lyrics.

Shows an interactive architecture graph for any model hosted on Hugging Face.

Predicts descriptive tags for an illustration using the WaifuDiffusion tagger models.

Segments the main subject of an image with BiRefNet and returns a transparent-background cutout.

Turns an image into a short video clip with Wan 2.2 and KV adapters.

Paint over an unwanted object in a photo and the inpainting model fills the gap.

Creates logo-style images from a text description using a FLUX LoRA.

WebGPU-accelerated Whisper that turns microphone or file audio into text locally in the browser.

Fills in or replaces masked image regions guided by a text prompt.

Convert document page images to structured text with IBM's compact Granite-Docling model.

Try a collection of LoRA styles on top of the FLUX.2 Klein image model.

Recommended for free users

Click on objects in an image to cut out segmentation masks using Segment Anything in the browser.

Describe a small app and get generated code that previews in the page.

Converts a rough sketch into cleaner line art.