#53 · Primary category: Image Generation
ComfyUI_UltimateSDUpscale
ComfyUI nodes for the Ultimate Stable Diffusion Upscale script by Coyote-A.
Project last updated:06/22/26
GitHub Stars
1.6K
Forks
120
Contributors
9
License
GPL-3.0
Why we included this project
Anyone who upscales large images with Stable Diffusion has probably hit the wall where the model either runs out of memory or leaves the upscaled image looking soft. This node set works around that by chopping the picture into tiles, running each one through the image-to-image diffusion pass, and stitching the results back together. Tiling is what lets it recover fine detail that a plain upscaler misses, and it keeps memory use low because the model only ever sees a tile-sized chunk. Since it is a direct port of the Ultimate SD Upscale script from the Automatic1111 ecosystem, the parameter behavior will feel familiar if you have used that tool before. The repo also ships documentation for the node parameters, example workflows, and templates reachable right inside the ComfyUI interface.
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.