#54 · Primary category: Image Generation
ComfyUI-SUPIR
SUPIR upscaling wrapper for ComfyUI
Project last updated:04/29/26
GitHub Stars
2.3K
Forks
124
Contributors
6
License
Other
Why we included this project
For photo upscaling and restoration work in ComfyUI, this is the integration that most people reached for before SUPIR landed in core. It packages SUPIR's SDXL image-to-image pipeline as a set of custom nodes, with a dedicated denoise-encoder VAE path, more sampler options, and lighter memory use than the original reference implementation. The split into multiple nodes means you can replace the bundled preprocessing with any other upscaler or restore model, so it fits into larger pipelines instead of dictating one fixed flow. SUPIR is now available natively in ComfyUI core, so these nodes mainly serve people on older versions or those who want the legacy workflow. The example workflows and pruned checkpoints make it easy to get realistic results for high-resolution photo enhancement and old-photo restoration.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
stable-diffusion-webui
Stable Diffusion web UI
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
upscayl
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
InvokeAI
InvokeAI is a leading open-source creative engine for Stable Diffusion, offering an industry-leading web UI for generating and editing visual media.