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.

Browser image tool that edits pictures, generates images from text, upscales them and removes watermarks.

Edits an image from a text instruction, with a selection of LoRA styles for the Qwen Image Edit 2511 model.

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

Upscales and enhances images, reproducing the Clarity AI upscaler with the Refiners library.

Edits images from text instructions, combining FireRed-Image-Edit with Qwen-Image-Edit-Rapid.

Text-to-image tool for FLUX.1 with a picker of more than 270 LoRA styles to apply.

Removes the background from an image using the BRIA RMBG 2.0 model.

Edits an image from a text instruction, with a selection of LoRA styles for the Qwen Image Edit 2509 model.

Generates images with FLUX.1 and lets you pick from more than 100 LoRA styles.

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

Edits images with Qwen-Image-Edit and a set of LoRAs, including one that locks a pose from a reference image.

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

Swaps the head in an image using the BFS LoRA on Qwen-Image, with a faster turbo option.

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

Generates illusion-style artwork with a diffusion model.

Edits images with Qwen Image Edit using a collection of selectable LoRAs.

Generates high-resolution images from text prompts with the RealVisXL Turbo model.

Extends an image beyond its borders by generating new content around it, using diffusion models.

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