ComfyUI
Open-source node-based app for AI images, video, audio and 3D
Makes video, audio and 3D as well as images, and has new releases in 2026; the last AUTOMATIC1111 release was 1.10.1 in February 2025.
Stable Diffusion web UI is a browser interface for Stable Diffusion, built with the Gradio library. It creates images from text (txt2img) and changes existing images (img2img). It also has inpainting, outpainting, upscaling, face restoration, training of embeddings and a tab to merge model checkpoints.
It runs on your own computer and needs Python and git. The README gives install steps for Windows and Linux with NVIDIA, AMD and Intel hardware, and the wiki covers Apple Silicon Macs. An API is turned on with the --api option. The wiki also lists online services, such as Google Colab, that can run it.
It is free and open source under the GNU Affero General Public License v3.0 (AGPL-3.0). The project lists no paid plans.
The README states support for video cards with 4 GB of memory. The latest release on the GitHub releases page is version 1.10.1, published on 9 February 2025. The last code change, on the development branch, was in March 2026 (checked October 2026).
Made for
People who want to run Stable Diffusion image models on their own computer through a browser interface, with NVIDIA, AMD or Intel hardware or an Apple Silicon Mac.
Use cases
- Generate images from text prompts
- Change existing images with img2img and inpainting
- Extend images past their borders with outpainting
- Upscale images and restore faces
- Train embeddings and hypernetworks on your own images
- Merge up to 3 model checkpoints into one
An alternative to
- ComfyUI
One page of settings (txt2img, img2img, inpaint) instead of a node graph.
Alternatives to Stable Diffusion web UI (AUTOMATIC1111) 4
InvokeAI
Open-source app for AI image generation with a canvas and node workflows
A layered canvas, node workflows and a model manager, with new releases in 2026 (6.14.2 in September 2026).
Stable Diffusion WebUI Forge
Local web interface for AI image generation, built on Stable Diffusion WebUI
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.
SwarmUI
Local web interface for AI image, video and audio generation, built on ComfyUI
Runs image and video models such as Flux, Wan and LTX-2 through the ComfyUI backend, and splits work across several GPUs or machines.
Discussion
Sign in to join the discussion