Okay, my intention wasn't to create a realistic checkpoint, or rather it was, but in the Furry segment. It turns out that the fur wasn't turning out the way I wanted. No matter how much I trained, Pony seems to have limitations that prevent me from getting a silky, realistic fur with clarity and sharpness. However, during my tests I realized that this model really wanted to be a Realistic PDXL model. So I've tried my best to bring the SD 1.5 feeling at max quality, I hope you enjoy it...

Recommended Sampling:

DPM++ 3M SDE
SGM Uniform
70 steps
CFG 8

About DPO (Direct Preference Optimization).

DPO fine-tune on datasets scored as highly visually appealing by an aesthetics classifier, to bias the model to visually appealing generations, while maintaining distributional guarantees and improving generic text-image alignment in addition to visual appeal. The training is via gradient descent, automatically validate checkpoints with the 500 unique prompts of the Pick-a-Pic validation set: measuring median PickScore reward of generated images. DPO scheme implicitly learns the differences in between images by taking an expectation over the inner term of the prompt.

So, DPO pay more attention on your prompt and try to generate a better image from it.

I'm very grateful to the authors of the Checkpoints and LoRAs used in the ONE FOR ALL series and I recommend everyone to visit them and appreciate their work (if your name isn't here, it's because any of your assets were been used):

And to all those who in some way collaborated or encouraged this work, I affectionately offer this simple but sincere Special Thanks:

Special Thanks to those creators:

Special Thanks to my amazing followers:

AND YOU WHO IS AMAZING TO READ SO FAR HERE!! WOW!! 😱🤩💓

YOU ARE REALLY AMAZING!! THANK YOU VERY MUCH!! 🥰🥰🥰

0 comment