☑️If you like my work, leave a review. I really appreciate them!✍️
Hot Melon [PonyXL] Style Lora. I recommend using 1.0 Strength using this with AutismMix SDXL for best results.
Trigger Word: there is no trigger word
Use "censored" and "mosaic censoring" when generating NSFW (completely optional)
Please look at prompts used in example images for help!
I use additional tools for my generations so my images may be different from yours. If you want to know what I use, please look at my guide.
My Socials | Support me on Patreon or Ko-fi (If you want)
Description
FAQ
Comments (6)
What are the parameters you're using, how much time it took to train and which GPU?
I'm taking 2 to 3 hours on a 3090 for PonyXL based models; 2400 steps
I have a 4070 and it takes 20-40 minutes at 1024x1024 depending on the amount of steps
@guy907223982 Is it possible for you to train a lora if we can give you a ready dataset?
@Rating_Agent yes but i would rather build the dataset myself.
@guy907223982 could you disponibilize your training parameters .json file?
first time se this artist for hot melon