Easy Diffusion
A free local AI image generator that runs Stable Diffusion on Windows, Linux and macOS, with a browser interface for prompts, image editing and ControlNet.
Easy Diffusion runs Stable Diffusion on your own computer through a browser interface. It's for people who want to generate and edit images locally without assembling the software components themselves. The free distribution bundles the required software and works on Windows, Linux and macOS.
You can create images from text, use an existing image as a starting point, or replace selected areas with inpainting. ControlNet lets you guide composition with a pose or outline, and a built-in drawing tool provides another way to sketch an input. Negative prompts and weighted words give you control over what appears. GFPGAN handles face correction, while RealESRGAN upscales the results.
The task queue accepts multiple prompts so you can prepare work while another image is generating. Live previews show progress, and style modifiers help you try different looks. You can generate variations of an image or compare prompt variations, then save results to your computer as JPEG, PNG or WEBP files.
It supports Stable Diffusion XL and custom models in .ckpt and .safetensors formats. The v4 engine adds Ernie, Z-Image, Flux, Lumina, Anima and quantized models. Model merging, custom VAEs and textual inversion embeddings give experienced users room to experiment; community UI plugins can extend the interface.
Windows and Linux users can run generation on NVIDIA or AMD graphics cards, or use the CPU. Multiple GPUs can share queued tasks. Easy Diffusion also scans models with picklescan and supports safetensors loading. Its custom license includes restrictions on harmful and unlawful generated content.
