Hello there and thanks for checking out this workflow!
—Intro—
SUPIR is a very powerful detailing/image-restoration model, capable of producing mind-blowing results, but usually requires some tweaking to do so,...
unless you have a setup that just works™, no matter the input.
Use-cases :
• (Hyper-)detailing generated images, even if they already are of high resolution and quality
• Photo-restoration tasks to get low-res and blurry content up to scratch again.
—Features—
Installation and download guide for models and nodes
►INFO guides explaining various settings
Upscaling
Florence 2 + WD14 prompting assistance
100 Steps to SUPIR — Journey to become a better image
—Custom Nodes used—
All of which can be installed through the ComfyUI-Manager
—Troubleshooting—
If nodes show up red (failing to load), check the 'Install Missing Custom Nodes' tab of the ComfyUI Manager for the missing node packs and install them.
Please check if all custom node packs load properly after installing, i.e. no
(IMPORT FAILED)messages next to any of them in the console upon ComfyUI startup.Always reload/drag'n'drop the original, downloaded workflow file into ComfyUI to reload an intact version of the workflow.
→ The last opened workflow that appears on startup shows a cached version of the workflow, "remembering" group nodes that failed due to missing nodes as failed, keeping them broken even after having everything installed correctly.
—Thanks—
The workflow would not be possible as is without these custom node packs. If you want to support the custom node creators, give them a ⭐ on their github repos! Thank you!
Feel free to ask any questions, share improvements or suggestions in the comment section!
Also let me know if you encounter any confusing points I can elaborate on and focus on improving for the next update!
Description
v1 — initial release
FAQ
Comments (6)
Amazing work.
I am new to comfyui. When I tried to run it, I got these red circles. I realized that they should be connected to other nodes, but I don't know where they should be connected.
Please let me know.
Thank you very much and welcome to ComfyUI!
From the cropped image I can only guess that you did not choose an image in the 'Load Image' node at the top of the [Input Image Settings] group. Is that the issue?
@redpinkretro Thank you for your reply,I uploaded a picture and the problem still exists. I think the problem is with the wifi Node. In the picture, the 'color match' node did not receive the 'image_ref' and ' image_target', 'input image size' and 'output image size' also received no information.
@catroskysan940 Ah, found the issue. The Color Match node must have been restored at some point, as the inputs are not named correctly. When you look at the example image : https://civitai.com/images/21113506
you can see how the inputs should be named.
The way wifi nodes ('Anything Everywhere?') work is through those names like a sender/receiver kind of system. When you right-click on the actual inputs of the Color Match node you can type in the exact names and it should work again. Or alternatively you could just download the workflow's base version again.
I will update it soon, too as some node layouts changed and to incorporate the florence2 node for auto-captioning in case of not having the prompt for an image.
@redpinkretro Thanks for your help, you did amazing work, now the v1 version works great, I will download the v2 version to try it.
@catroskysan940 Thank you very much! Glad it works for you now!