Everything in the catalog

Removes unwanted objects from a photo and upscales images using models that run in the browser.

Stable Diffusion that runs completely in the browser through WebGPU, with no server-side inference.

Generates and interpolates between short melodies and drum patterns using a variational autoencoder in the browser.

Play a few buttons and a neural net turns them into a full piano performance in your browser.

Transcribes piano audio into MIDI notes in the browser using the Onsets and Frames model.

Volunteer-run network where anyone can generate images and text for free, even anonymously.

Web front end for generating Stable Diffusion images on the AI Horde volunteer GPU network.

Shows a garment photo on a person photo so you can preview how clothing would look.

Text-to-image generation with the FLUX.1 dev model.

Fast text-to-image generation with the few-step FLUX.1 schnell model.

Meta MusicGen demo that composes a short clip from a prompt, optionally following a melody.

Sets a 3D camera position to regenerate an image from another viewpoint.

Finds a text prompt, including style and artist hints, that matches a given image.

Generates images that keep the identity of a face in your uploaded photo.

Expands a short idea into a longer, more detailed Stable Diffusion prompt.

Animates a single picture into a short video with Stable Video Diffusion.

Quick text-to-image generation with the Z-Image Turbo model.

Official demo of the Stable Diffusion 3 Medium text-to-image model.

Builds detailed text-to-image prompts for FLUX from a few chosen options and keywords.

Generates descriptive captions of images for training data or prompts.

Writes descriptive captions for images in several styles such as descriptive or training-prompt format.

Official demo for generating and editing images with FLUX.2 dev.

Turns a face photo into an anime-style image with AnimeGANv2.

Quickly reconstructs a textured 3D asset from one image.