Welcome to clamPDXL, an attempt to port the art style of my Find&ForgetYou and Find&ForgetYou - Anime series of checkpoints to PonyXL. Trained on a pruned dataset of images generated on these checkpoints and uploaded to CivitAI (so really, this is your fault as much as it is mine), and merged with AutismMix_confetti.
Some may prefer 3d in negative - it's up to you! Check out the first two images in the gallery for the difference.
source_anime in the positive prompt will also give more anime-like results. I did not use this in any sample images, but check out the gallery below for examples!
Have fun!
Description
rebaked the F&FY style as a DoRA with some more images to fill in some blank spots. removed all other ingredients. closer to what I wanted style-wise than v2, while (hopefully) being a bit more flexible.
FAQ
Comments (12)
Based, as the kids say
I'm trying to do something similar to your achievement with my own checkpoint. Do you have a more specific method/steps/settings/etc. for your process?
Wellp, this immediately became my favorite XL model.
God Bless You Clam! You are doing his work on this planet!
My favorite PonyXL model. But I have one problem, sometimes it is generating "colorful mess" with a well composed prompt, any suggestions how to fix it?
One giant leap for mankind. You've done a great job bringing your style to Pony!
This is the best model I've tried. It seems to know more concepts than most, its reliable and pleasing. I always use findandforget to test prompts before going on to other models, Slap Like!
Pretty solid Pony checkpoint for semi-realistic models.
well done
Hi. Does it work on a MAC? Because the SDXL models don't work for me. :(
My new favourite checkpoint 😍
Thank you for the 69 buzz! 🤣
Why is this model not available for on-site generation? :(