HELLO! I am RAMTHRUST and I am pleased to present to you my daily driver workflow.
This workflow is something exceptional but VRAM heavy. It's so VRAM heavy that I think you need a MINIMUM of 16GB of VRAM.
It's slow, it's ugly, but godDAMN does it produce high quality images!
There are TONS of notes inside with download links to all of the detailers and other items you'll need to dance with the devil IN SDXL VERSION 1.01.
Basically, the process is as follows:
Get those missing resources, you should know how to do this in comfyui. There are download links in all of the notes for maximum convenience
native image gen - you know how to do this
preview chooser - choose the image(s) you want to upscale and hit proceed
If everything is in place, you should get a fantastic 2x upscaled image at the end.
There are multiple save points in this flow: The native generation, the latent upscale (on pass 2) and the detailer pass. I created so many save points because sometimes things go wrong and you may want to make comparisons without re-genning
IF YOU HAVE ANY QUESTIONS HOP INTO THE DISCORD GEN CHAT AND ASK FOR @RAMTHRUST and I will give you a hand.
I'm serious when I say that this upscaler is the bomb and I DON'T use anything else.
Please enjoy!
@RAMTHRUST
Special thanks to @CHESHIRE_OS because I'm a big fat front-end thief!
Description
WORKS WITH SDXL AND ALL SPIN-OFF MODELS SUCH AS PONY AND ILLUSTRIOUS.
FAQ
Comments (13)
Back again! So yeah these are still the best workflows (in my opinion) and your FLUX one is top level. 10/10 yo. Thanks for the work!
Thanks man, I appreciate it. I made a few adjustments with the flux one so that should be coming soon; big speed boost with minimal quality loss.
@RAMTHRUST Cant wait to see! I had compile/sage/teacach i added in but it didnt change anything much so im excited to see what you did too
Excellent work flow. Excels in many areas. Easy to understand even for those like me that are relatively new to Comfyui. GOD tier upscaling , and highly efficient . This is my go to work flow . I have no need to use anything else, since it produces the results "I am happy with" . Thanks and keep up the great work!
0/10
Не беритесь за те вещи в которых не понимаете
Please fix embeddings/textual inversion error.
This new newest Ver 4.0 workflow is great, but every-time I use any of my textual inversion, I get an error coming from one of the save nodes. I don't know what it is. Please fix.
@RAMTHRUST you mention the notes have downloads for the upscalers etc used, but the workflow has only a single note with no such links.
Could you please provide links to recommended upscaler models, detailers, etc (preferably available on Civit AI)? I am struggling to find them my side. I am using an Illustrious model as the checkpoint if that makes any difference.
Hey dude!
The links are only in 1.01, but I pulled them for you and will put them in the model page. I also have to confess, the Ramthrust Demigod Upscaler is basically legacy at this point. Every time comfy updates, it breaks. It can be fixed in a lot of cases, but I know some nodes here need to be outright replaced. Here are the detailers!
Face Detailer: https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8m.pt
Hand Detailer: https://huggingface.co/Bingsu/adetailer/resolve/main/hand_yolov8n.pt?download=true (RECOMMENDED)
Clothing Detailer: https://huggingface.co/Bingsu/adetailer/resolve/main/deepfashion2_yolov8s-seg.pt?download=true
Hair Detailer: https://github.com/hben35096/assets/releases/download/yolo8/hair_yolov8n-seg_60.pt
Skin Detailer: https://github.com/hben35096/assets/releases/download/yolo8/skin_yolov8m-seg_400.pt
Eye Detailer: https://civitai.com/api/download/models/200389 (RECOMMENDED)
There are more out there though, and the eye detailer has been updated too. Give these a shot and let me know if you need a hand.
Possible new release soon. Should be MUCCCCCCCCCCCCCCCCCH neater