ComfyUI
Open-source node-based app for AI images, video, audio and 3D
Makes video, audio and 3D as well as images. A desktop app for Windows, macOS and Linux, and Comfy Cloud for computers without a GPU.
Local web interface for AI image generation, built on Stable Diffusion WebUI
Stable Diffusion WebUI Forge is a platform on top of Stable Diffusion WebUI (AUTOMATIC1111), built with Gradio. The README says it aims to make development easier, optimize resource management, speed up inference and study experimental features. It is based on SD-WebUI 1.10.1.
It runs locally on your own computer and GPU. A one-click package for Windows includes Git and Python; the recommended package uses CUDA 12.1 and PyTorch 2.3.1. It supports Flux models in BitsandBytes NF4 and GGUF formats, LoRAs, built-in ControlNet, IP-Adapters and images with transparent backgrounds (LayerDiffuse).
It is free and open source under the AGPL-3.0 licence.
The README says Forge is under construction and that docs, UI and functionality may change with updates. Its status table was last updated in September 2024 and marks some parts as broken or not yet implemented. The last code change on the main branch was in June 2025, with none since (checked October 2026).
People who generate AI images with Stable Diffusion and Flux models on their own GPU, and developers who build extensions. The README says Forge aims to make development easier and to study experimental features.
Keeps the AUTOMATIC1111 interface and adds Flux models (NF4, GGUF), built-in ControlNet and transparent images. Its README says it speeds up inference and manages GPU memory better.
One page of settings instead of a node graph, with ControlNet and IP-Adapters built in.
Open-source node-based app for AI images, video, audio and 3D
Makes video, audio and 3D as well as images. A desktop app for Windows, macOS and Linux, and Comfy Cloud for computers without a GPU.
Discussion
Sign in to join the discussion