ComfyUI is a powerful and modular stable diffusion GUI with a graph/nodes interface. It allows users to design and execute advanced stable diffusion pipelines with a flowchart-based interface. It supports SD1.x and SD2.x and offers many optimizations, such as re-executing only parts of the workflow that change between executions. It also supports loading checkpoints and safetensors models, and various upscaling models (ESRGAN, ESRGAN variants, SwinIR, Swin2SR, etc.). It can also save/load workflows as JSON files, and generate and load full workflows from PNG files.
github.comGitHub
Upvotes
121
Pricing
GitHub
Category
Generative Art
In the database since
Mar 2023
Overview
About ComfyUI
Newsletter
Tools like this change fast
New Generative Art tools launch every week — the newsletter keeps you ahead of what's worth trying.
GitHub Repository
Note: This is a GitHub repository, meaning that it is code that someone created and made available for others to use. It typically requires some technical knowledge to set up and run.
See it in action
Videos featuring ComfyUI
Keep exploring
Similar AI tools
AI news twice a week
Join 250,000+ readers getting the most important AI news and coolest tools every Wednesday and Friday.

